Printing detection method and intelligent perception rotary screen printing machine using this method

Abstract

The present invention discloses a printing detection method and an intelligent perception rotary screen printing machine applying the method, including: Step S100: Before printing starts, determine N color sets and determine color set features according to the color sets; Step S200: After the printing is completed, an image acquisition device acquires a printing image in real time and determines printing features according to the printing image; Step S300: Compare the printing features with the color set features and output whether there is misprint according to the comparison result. In the present invention, the number N of color sets is determined before printing starts. The controller of the printing device determines color set features according to the N color sets. The image acquisition device acquires the state of the printing in real time during the printing process and determines printing features according to the acquired printing image. The controller compares the printing features with the color set features, and the controller determines whether there is a misprint phenomenon according to the comparison result.

Description

Technical Field

[0001] The present invention relates to the technical field of textile printing and dyeing equipment, and particularly to a printing detection method and an intelligent perception rotary screen printing machine applying the method. Background Art

[0002] The fabric printing and dyeing technology in the textile industry is a highly professional applied engineering technology. At present, printing is still a major branch in the textile printing and dyeing industry. In the printing industry, the phenomenon of "flower escape" is very likely to occur due to various factors, resulting in poor guarantee of the pattern registration accuracy of products.

[0003] The independently driven rotary screen printing machine is developed on the basis of the overall driven rotary screen printing machine. The rotary screen printing machine usually has multiple independent rotary screens, generally ranging from 4 to 18 color sets. When a group of rotary screens is selected, the printed pattern is correspondingly determined. For example, a 16 - rotary - screen printing machine is called a 16 - color - set printing machine. During the printing process, the fabric blank is firmly attached to the printing guide belt and runs continuously, passing through each rotary screen pressed tightly on the fabric surface in turn. The squeegee inside the screen evenly squeezes the color paste onto the blank through the pattern mesh, thus completing the printing. Each rotary screen has an independently driven control motor on the screen head to control the rotary screen speed. The length of the pattern printed on the fabric when the rotary screen rotates one circle is called a flower repeat. If during the printing process, the printing of one of the rotary screens does not match the designed pattern position, resulting in the flower repeat being ahead or behind, the printed fabric will be a defective product, which is the so - called "pattern misregistration" (also known as "flower escape") phenomenon. Therefore, it is necessary to detect the printing during the printing process.

[0004] The main detection means for printing in the prior art is the detection method based on color marks. Specifically, zero - position detection marks are set on the rotary screen or the control motor, and then the distance between the marks is detected by an optoelectronic method or whether the marks left by the rotary screen on the fabric are offset is detected by an image method to achieve the purpose of automatic pattern registration. However, both of these methods detect the marks on the printing rotary screen or the fabric, rather than directly detecting the printing pattern on the fabric. Therefore, for the "pattern misregistration" phenomenon caused by the deformation of the fabric on the guide belt and the asynchronous running speeds between the guide belt and each screen cylinder, it is still impossible to detect, and only manual intervention can be used. Summary of the Invention

[0005] To solve at least one of the problems existing in the above - mentioned prior art, according to one aspect of the present invention, a sliding component, a device, and a system having the sliding component are provided to solve the problem that the existing sliding component is difficult to disassemble and assemble.

[0006] The object of the present invention can be achieved by the following technical solutions: A printing detection method includes:

[0007] Step S100: Before starting printing, determine N color sets and determine the color set features according to the color sets;

[0008] Step S200: After the printing is completed, the image acquisition device acquires the printing image in real time and determines the printing features according to the printing image;

[0009] Step S300: Compare the printing features with the color set features and output whether there is a printing error according to the comparison result.

[0010] Preferably, step S100 further includes:

[0011] Step S101: After determining the quantity and color of each color set, generate N color set templates for the N color sets;

[0012] Step S102: Add the N color set templates to generate a composite image;

[0013] Step S103: Extract the color set features of the composite image.

[0014] Preferably, step S100 further includes:

[0015] Step S104: Obtain the coordinates of the color set features.

[0016] Preferably, step S300 further includes:

[0017] Step S301: Perform filtering processing on the printing image, and adjust the proportion of the filtered printing image so that the image proportion of the printing image is the same as the image proportion of the color set features;

[0018] Step S302: Extract the printing features of the printing image;

[0019] Step S303: Compare the printing features with the color set features and output whether there is a printing error according to the comparison result.

[0020] Preferably, step S300 further includes:

[0021] Step S304: After determining a printing error, obtain the ROI region, and calculate the relative offset in the ROI region using the FTDT curve matching;

[0022] Step S305: Adjust the circular screen phase according to the relative offset.

[0023] Preferably, step S300 further includes:

[0024] Step S306: After adjusting the circular screen phase, perform a re-detection on the printing. If a printing error is found again, a prompt is issued.

[0025] Another object of the present invention is to provide an intelligent sensing rotary screen printing machine, which is characterized by comprising a device main body, a plurality of rotary screens, a plurality of control motors, a controller and an image acquisition device, and the plurality of rotary screens, the plurality of control motors, the controller and the image acquisition device are arranged on the main body; the controller is used for controlling the control motors; each control motor is used for driving the corresponding rotary screen to rotate to print on the fabric, and the image acquisition device is used for acquiring the printed image on the fabric and transmitting the printed image to the controller; the printing device also applies the above-mentioned printing detection method.

[0026] Preferably, the intelligent sensing rotary screen printing machine further comprises a printing guide belt, and the plurality of rotary screens are sequentially arranged above the printing guide belt from the proximal end to the distal end.

[0027] Preferably, the image acquisition device is arranged above the printing guide belt and adjacent to the distal end of the last rotary screen.

[0028] Preferably, the image acquisition device is a line array camera.

[0029] Compared with the prior art, before starting printing, the present invention first determines the number N of color sets, the controller of the printing device determines the color set characteristics according to the N color sets, the image acquisition device collects the state of the printing in real time during the printing process, and determines the printing characteristics according to the collected printed image, and the controller compares the printing characteristics with the color set characteristics, and the controller determines whether there is a printing error according to the comparison result. In addition, after determining the printing error, the present invention can also obtain the ROI region, and use the FTDT curve matching in the ROI region to calculate the relative offset of the printing error, so as to identify the rotary screen that sends the printing error; at the same time, send the relative offset of the printing error to the controller, and the controller adjusts the rotary screen according to the relative offset, without manual intervention. Description of the Drawings

[0030] Figure 1 It is a schematic structural diagram of an intelligent sensing rotary screen printing machine in an embodiment of the present invention;

[0031] Figure 2 It is a schematic diagram of the printing detection method in an embodiment of the present invention;

[0032] Figure 3 It is a schematic diagram of the printing detection method in one embodiment of the present invention Figure 1 ;

[0033] Figure 4 It is a schematic diagram of the printing detection method in one embodiment of the present invention Figure 2 ;

[0034] Figure 5Schematic diagram of the printing detection method according to one embodiment of the present invention Figure 3 ;

[0035] Figure 6 Schematic diagram of the printing detection method according to one embodiment of the present invention Figure 4 ;

[0036] Figure 7 Schematic diagram of the printing detection method according to one embodiment of the present invention Figure 5 。 Detailed implementation manners

[0037] For better understanding and implementation, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0040] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0041] Please refer to Figure 1 , the present invention discloses an intelligent perception rotary screen printing machine 100, including a device main body 110, a plurality of rotary screens 120, a plurality of control motors 130, a controller 160 and an image acquisition device 140. The plurality of rotary screens 120, the plurality of control motors 130, the controller 160 and the image acquisition device 140 are arranged on the main body 110; the controller 160 is used to control the control motors 130; each control motor 130 is used to drive the corresponding rotary screen 120 to rotate to print on the fabric, and the image acquisition device 140 is used to acquire the printing image on the fabric and transmit the printing image to the controller 160.

[0042] Specifically, the device main body 110 functions as a bracket, and multiple components can be installed on the device main body 100. The device main body 110 has a proximal end A and a distal end B. The proximal end A is the input end, and the distal end B is the output end. The fabric enters the device main body 100 from the proximal end A and is transmitted in the direction of the distal end B. During this transmission process, each circular screen 120 presses tightly against the surface of the fabric. The controller 160 can control the rotation speed of each control motor 130. Thus, under the drive of the control motor 130, a squeegee (not shown in the figure) inside the circular screen 120 squeezes the color paste evenly onto the surface of the fabric through the pattern mesh. After passing through all the circular screens 120, the printing is completed. After the printing is completed, the image acquisition device 140 located at the distal end B acquires the printed image in real time and transmits the printed image to the controller 160. The controller 160 can determine whether there is a printing error based on this printed image. If there is a printing error, the control motor 130 corresponding to the circular screen 120 with the printing error is adjusted. Thus, it is possible to automatically adjust the corresponding circular screen 120 when a printing error is detected without manual intervention.

[0043] In some embodiments, the printing device 100 further includes a printing guide belt 150. The printing guide belt 150 is disposed on the upper surface of the device main body 110. A plurality of the circular screens 120 are sequentially arranged above the printing guide belt 150 from the proximal end A to the distal end B. The printing guide belt 150 is located between the device 110 and the circular screen 120, and the gap between the printing guide belt 150 and the circular screen 120 is small. The printing guide belt 150 is used to drive the fabric to move from the proximal end A to the distal end B. Therefore, the fabric can be tightly pressed by all the circular screens 120 to complete the printing.

[0044] In some embodiments, the image acquisition device 140 is disposed above the printing guide belt 150 and adjacent to the distal end B of the last circular screen 120. Through the above arrangement, after the printing is completed, the image acquisition device 140 can immediately sample the printed image and transmit it to the controller 160. The controller 160 can realize real-time detection of whether there is a printing error in the printed image.

[0045] In some embodiments, the image acquisition device is a line array camera.

[0046] As Figure 2 shown, the present invention also discloses a printing detection method, including:

[0047] Step S100: Before the printing starts, determine N color sets and determine the color set features according to the color sets; Step S200: After the printing is completed, the image acquisition device acquires the printed image in real time and determines the printing features according to the printed image; Step S300: Compare the printing features with the color set features and output whether there is a printing error according to the comparison result.

[0048] Specifically, before the printing starts, determine the number N of color separations used and their corresponding colors, and input them into the controller 160. The controller 160 determines the color separation features based on the N color separations. The selection of color separation features can be pixel-based or features such as edges, corner points, gray-level co-occurrence matrices, etc. Then start running the printing device 100. Place the fabric at the input end of the printing device 100 (i.e., the proximal end A). Driven by the printing guide belt 150, the fabric moves from the proximal end A to the distal end B. Therefore, the fabric can be tightly pressed by all the screen cylinders 120 to complete the printing. After the printing is completed, the image acquisition device 140 can immediately sample the printed image and transmit it to the controller 160. Since there is noise in the process of sampling the printed image, filtering processing is required. After filtering, the controller 160 determines the printing features based on the filtered printed image. Commonly used filters include mean filters, median filters, and bilateral filters, etc. The bilateral filter is a non-linear filter that takes into account both the spatial information and the gray-level information of the image. Compared with the mean filter and the median filter, it can retain the edge detail information and achieve the purpose of edge-preserving denoising.

[0049] Then, the controller 160 compares the printing features with the color separation features. If the printing features are consistent with the color separation features, there is no misprint; if the printing features are inconsistent with the color separation features, there is a misprint. When a misprint is found, the controller 160 can send a prompt to the operator. After receiving the prompt, the operator can know that there is a misprint, so that the printing device can be adjusted in time to avoid more misprints.

[0050] In some embodiments, the step S100 further includes:

[0051] Step S101: After determining the number and color of each color separation, generate N color separation templates for the N color separations; Step S102: Add the N color separation templates to generate a composite image; Step S103: Extract the color separation features of the composite image.

[0052] Specifically, after determining the number and color of each color separation, each color separation has its own template pattern. The controller generates N color separation templates according to the template patterns corresponding to the N color separations. Then, adding the N color separation templates can obtain a composite image. Then extract the color separation features of this composite image. The selection of color separation features can be pixel-based or features such as edges, corner points, gray-level co-occurrence matrices, etc. Preferably, the selection of color separation features is based on edge features. After determining the color separation features, the controller 160 generates a color separation feature template and then saves this color separation feature template for subsequent comparison. Through the above settings, before the printing starts, the color separation feature template is pre-generated. During the subsequent detection process, the controller 160 can directly call this color separation feature template, saving comparison time and improving detection efficiency.

[0053] In some embodiments, the controller 160 divides the above color separation feature template into M sub-feature templates, and each sub-feature template contains at least one color separation feature. Through the above settings, a large color separation feature template is disassembled into M sub-feature templates. Since the sub-feature templates are smaller, the amount of computation during comparison is also smaller. As long as the color separation feature of one of the sub-feature templates is inconsistent with the corresponding printing feature, it can be determined that there is a printing error, and there is no need to detect other sub-feature templates. Therefore, the efficiency of determining whether there is a printing error can be greatly improved.

[0054] As Figure 4 shown, in some embodiments, the step S100 further includes: step S104: obtaining the coordinates of the color separation feature. Specifically, after the controller 160 generates the color separation feature template, the feature coordinates of the color separation feature on the color separation feature template can be determined. During the comparison process, only the printing feature located at the feature coordinates on the printing image needs to be compared, rather than comparing all the printing images with the synthetic image, thereby reducing the amount of computation and quickly determining whether there is a printing error.

[0055] As Figure 5 shown, in some embodiments, the step S300 further includes:

[0056] Step S301: performing filtering processing on the printing image, and adjusting the proportion of the filtered printing image so that the image proportion of the printing image is the same as the image proportion of the color separation feature; step S302: extracting the printing feature of the printing image; step S303: comparing the printing feature with the color separation feature, and outputting whether there is a printing error according to the comparison result. Specifically, the controller 160 performs filtering processing on the printing image from the image acquisition device 140. Since the filtering processing is a prior art, it will not be elaborated here. The proportion of the filtered printing image is adjusted so that the image proportion of the printing image is the same as the image proportion of the color separation feature. Through the above adjustment, the coordinates of the printing feature and the color separation feature on their respective images are the same. Therefore, during the comparison process, only the images at the corresponding coordinates need to be compared, thereby reducing the amount of computation, increasing the efficiency of determining whether there is a printing error, and when there is a printing error, it can be determined which one or which several screen cylinders 120 are offset according to the area where the printing error is located, thereby providing a basis for the operator or the controller 160 to adjust the screen cylinder 120.

[0057] As Figure 6 shown, in some embodiments, the step S300 further includes:

[0058] Step S304: After determining the misregistration, obtain the ROI region, and calculate the relative offset using FTDT curve matching in the ROI region; Step S305: Adjust the circular screen phase according to the relative offset.

[0059] Specifically, in image processing, the area to be processed is outlined in the form of a rectangle, circle, ellipse, irregular polygon, etc. from the image to be processed, which is called the region of interest (ROI). Various operators and functions are commonly used in machine vision software such as Halcon, OpenCV, and Matlab to obtain the ROI of the region of interest and perform the next step of image processing. In this embodiment, after determining the misregistration, at least one ROI region including the misregistration is determined in the image, and then the relative offset is calculated using FTDT (Fourier transform displacement theorem) curve matching. The displacement of the image based on phase correlation in the time-domain signal can be manifested by the change of phase in the frequency domain.

[0060] Suppose f1(x, y) and f2(x, y) are two image signals, and f2(x, y) is obtained by translating f1(x, y) by (dx, dy), that is, it satisfies

[0061] f2(x, y) = f1(x - dx, y - dy)

[0062] Reflecting it into the frequency domain, FTDT can be expressed as

[0063] F2(u, v) = F1(u, v) × exp[-i2π(udx + vdy)], (1)

[0064] In the formula: F1(u, v) and F2(u, v) are the Fourier transforms corresponding to f1 and f2 respectively, where u is the abscissa of the frequency-domain graph; v is the ordinate of the frequency-domain graph.

[0065] Dividing the left side of formula (1) by the right side, the cross-power spectrum of f1(x, y) and f2(x, y) is obtained. Taking the inverse Fourier transform of the cross-power spectrum can obtain an impulse function (called the Dirac impulse function) at the point (dx, dy), and the relative offsets dx and dy can be found by determining the peak coordinates of this function. Therefore, the relative offset of the corresponding circular screen 120 can be determined through this relative offset, which is convenient for the operator or the controller 160 to accurately adjust the circular screen 120.

[0066] As Figure 7 shown, in some embodiments, the step S300 further includes:

[0067] Step S306: After adjusting the phase of the circular screen, re-inspect the printing. If misregistration is found again, a prompt is issued. The operator or the controller 160 adjusts the phase of the corresponding circular screen 120 according to the above relative offset. After the adjustment is completed, the controller 160 re-inspects the printed matter after the adjustment. If misregistration still occurs, a prompt is issued and the adjustment is carried out again until no misregistration occurs. Through the above settings, rapid adjustment can be achieved, the generation of misregistration can be reduced, and the production efficiency can be improved.

[0068] The printing device of the present invention applies the above printing detection method to improve the detection efficiency and the production efficiency of good products.

[0069] The technical means disclosed in the solution of the present invention are not limited to the technical means disclosed in the above embodiments, but also include technical solutions formed by any combination of the above technical features. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications are also regarded as the protection scope of the present invention.

Claims

1. A printing detection method, characterized in that Including: Step S100: Before starting printing, determine N color sets and determine color set features according to the color sets; Step S200: After the printing is completed, an image acquisition device acquires a printing image in real time and determines printing features according to the printing image; Step S300: Compare the printing features with the color set features and output whether there is misprint according to the comparison result; Step S300 further includes: Step S301: Perform filtering processing on the printing image, and adjust the proportion of the filtered printing image so that the image proportion of the printing image is the same as the image proportion of the color set features; Step S302: Extract the printing features of the printing image; Step S303: Compare the printing features with the color set features and output whether there is misprint according to the comparison result; Step S300 further includes: Step S304: After determining misprint, obtain the ROI region, and calculate the relative offset in the ROI region by using FTDT curve matching; Step S305: Adjust the circular screen phase according to the relative offset; Step S300 further includes: Step S306: After adjusting the circular screen phase, perform re - detection on the printing. If misprint is found again, give a prompt.

2. The printing detection method according to claim 1, wherein Step S100 further includes: Step S101: After determining the quantity and color of each color set, generate N color set templates for the N color sets; Step S102: Add the N color set templates to generate a composite image; Step S103: Extract the color set features of the composite image.

3. The printing detection method according to claim 2, wherein Step S100 further includes: Step S104: Obtain the coordinates of the color set features.

4. Intelligent perception circular screen printing machine, characterized in that, It includes a device main body, multiple circular screens, multiple control motors, a controller and an image acquisition device. The multiple circular screens, the multiple control motors, the controller and the image acquisition device are arranged on the device main body; The controller is used to control the control motors; each control motor is used to drive the corresponding circular screen to rotate for printing on the fabric, and the image acquisition device is used to acquire the printing image on the fabric and transmit the printing image to the controller; The intelligent perception circular screen printing machine also applies the printing detection method according to any one of claims 1 - 3.

5. The intelligent sensing rotary screen printing machine according to claim 4, characterized in that, The intelligent perception circular screen printing machine further includes a printing guide belt, and the multiple circular screens are sequentially arranged above the printing guide belt from the proximal end to the distal end.

6. The intelligent sensing rotary screen printing machine according to claim 5, characterized in that, The image acquisition device is arranged above the printing guide belt and is adjacent to the distal end of the last circular screen.

7. The intelligent perception rotary screen printing machine according to any one of claims 4-6, characterized in that, The image acquisition device is a line - array camera.

Images