Color detection system and detection method for gold and silver card presswork without color marks

Abstract

The invention discloses a color detection system and detection method for a gold and silver card printed matter without a color mark, and the system comprises a printed matter placement platform which is used for placing a gold and silver card to be detected; the multispectral dome light source is used for performing light source irradiation on the to-be-detected gold and silver card; the multispectral camera is used for shooting an image of the gold and silver card to be detected under the irradiation of the multispectral dome light source; the image detection host is used for acquiring the to-be-detected gold and silver card image shot by the multispectral camera and performing color detection; wherein the multispectral camera and the multispectral dome light source translate relative to the printed matter placing platform. The multispectral dome light source is adopted, multispectral data can be obtained through one-time scanning, on one hand, color measurement can be conducted on high-glossiness materials such as gold and silver cards, and on the other hand, the problem that accuracy is reduced due to spectrum deficiency of spot color measurement can be solved; meanwhile, the imaging mode is low in cost, so that the problems of precision, efficiency and cost are solved.

Description

Technical Field

[0001] The invention relates to the field of printed matter image detection, and in particular to a color detection system and method for printed matter color without color mark gold and silver cards. Background Art

[0002] In the field of printing and image measurement, CMYK four-color printing plays an important role. The CMYK color model produces various colors based on the mixture of four inks: cyan, magenta, yellow, and keyplate / black. Although CMYK printing can produce a wide range of colors, it may not be able to express certain specific colors (such as highly saturated bright colors or metallic colors). In order to make up for this shortcoming, spot color printing was introduced. It uses specific inks to print colors that are difficult to obtain through CMYK mixing, such as gold and silver. Spot color printing can provide a wider color range than standard CMYK printing, so that certain colors that are difficult to obtain through CMYK ink mixing can be accurately reproduced on printed products. Spot color printing can achieve the following effects: (1) Enhanced color expression: By introducing spot colors, the color richness and expression of printed products can be significantly improved. (2) Expanded color gamut: Spot color printing can cover color areas that cannot be achieved by CMYK four-color printing. (3) Improve printing effects: In certain specific application scenarios (such as high-end packaging, advertising, etc.), spot color printing can significantly improve printing effects and make printed products more eye-catching.

[0003] For image detection of CMYK four-color prints, RGB three-color images are usually used. The RGB color model produces various colors based on the superposition of three colors: red, green, and blue. It is one of the most commonly used color models in digital image processing. In image measurement, RGB three-color images are widely used in the acquisition, processing, and analysis of color images. However, the acquisition of RGB three-color images also has certain limitations: for color measurement of high-gloss surfaces (such as gold cards, silver cards, lasers, etc.), conventional scanning equipment may not be able to accurately capture their color information. This is because high-gloss surfaces will produce reflections and glare, which interfere with the measurement accuracy of the scanning equipment. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a color detection system and method for colorless gold and silver card prints.

[0005] The objective of the present invention is achieved through the following technical solutions:

[0006] The first aspect of the present invention provides a color detection system for colorless gold and silver card prints, comprising:

[0007] Printing material placement platform, used to place gold and silver cards to be tested;

[0008] Multi-spectrum dome light source, used to illuminate the gold and silver cards to be inspected;

[0009] A multispectral camera, used to capture images of gold and silver cards to be inspected under the illumination of a multispectral dome light source;

[0010] The image detection host is used to obtain the image of the gold and silver card to be detected taken by the multi-spectral camera and perform color detection;

[0011] Wherein, the multi-spectral camera and the multi-spectral dome light source are both translated relative to the printed matter placement platform.

[0012] Furthermore, the multi-spectrum dome light source includes a dome device and a plurality of groups of LED light strips located below the dome device, and each group of LED light strips includes a plurality of groups of LED lamp beads with at least three different tones arranged in sequence.

[0013] Furthermore, in each cycle, each LED lamp bead with different hue is lit up respectively according to the acquisition frequency of the multi-spectral camera.

[0014] Furthermore, the printed matter placement platform absorbs and flattens the gold and silver cards to be tested by negative pressure adsorption.

[0015] The second aspect of the present invention provides a detection method for a color detection system for a colorless gold and silver card print as described in the first aspect, which is applied to an image detection host and comprises the following steps:

[0016] For the gold and silver cards to be inspected, we first obtain the corresponding reference sample images, which are used as the color standard and spatial content standard.

[0017] Obtain real-time samples of gold and silver cards to be inspected that are actually captured by the multispectral camera;

[0018] Perform image registration processing on the real-time sample according to the image and text characteristics of the reference sample, and obtain pixel-level registration after processing;

[0019] Calculate the color difference between the reference sample and the real-time sample.

[0020] Furthermore, after obtaining the real-time samples of the gold and silver cards to be detected actually collected by the multispectral camera, the real-time samples are preprocessed:

[0021] Pixel-level noise is removed through noise reduction technology;

[0022] Achieve spatial white balance through a white standard plate to eliminate brightness errors caused by factors including light source and lens;

[0023] Perform multi-color correction to achieve color white balance;

[0024] The multispectral information is converted into xyz space and then converted into Lab space to achieve color correction.

[0025] Furthermore, the image registration process includes:

[0026] Based on the sub-images of the four corners of the reference sample, a global search is performed in the image of the real-time sample to find the overall positioning point, confirm the scaling factor, and remove irrelevant content larger than the reference image, including background information of the scanning device and information other than the finished product design content, to obtain a rough positioning matching image;

[0027] Fine position matching is performed based on the reference sample and the coarse positioning matching map, and pixel-level alignment is achieved after position matching.

[0028] Furthermore, the color difference calculation of the reference sample and the real-time sample includes:

[0029] The color difference between each group of color blocks in the real-time sample and the corresponding color blocks in the reference sample is calculated, and the average color difference of each color block is calculated to globally evaluate the color difference.

[0030] Further, the color block is at least one color block of interest, and the average value of the color difference in the color block of interest is calculated, so as to globally evaluate the color difference; or:

[0031] The color blocks are weighted color blocks, and the color difference of each color block is multiplied by the corresponding weight to calculate the average value, so as to globally evaluate the color difference.

[0032] Furthermore, after obtaining the image of the corresponding reference sample, the smooth feature of the reference sample is judged: by searching the maximum value Max and the minimum value min of the three components of RGB in the size range, the difference ColorDiff = max-min is calculated, and when the difference ColorDiff> the color difference threshold Th_ColorDiff, the image smooth_mask is set to 255, and if the difference ColorDiff≤the color difference threshold Th_ColorDiff is set to 0, a relatively smooth area image smooth_mask is obtained;

[0033] When calculating the color difference between the reference sample and the real-time sample, when smooth_mask=255, the color difference is calculated, and when smooth_mask=0, the color difference is ignored.

[0034] The beneficial effects of the present invention are:

[0035] In an exemplary embodiment of the present invention, a multi-spectral dome light source is used to obtain multi-spectral data through a single scan. On the one hand, the color of high-gloss materials such as gold and silver cards can be measured, and on the other hand, the problem of reduced accuracy caused by the lack of spectrum in spot color measurement can be solved. At the same time, this imaging method has a low cost, thus solving the three problems of accuracy, efficiency and cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic structural diagram of a color detection system for color-free gold and silver card prints provided in an exemplary embodiment of the present invention;

[0037] Figure 2 A schematic diagram of an LED light strip of a multi-spectrum dome light source provided in an exemplary embodiment of the present invention;

[0038] Figure 3 A schematic diagram of an imaging process provided in an exemplary embodiment of the present invention;

[0039] Figure 4 It is a flow chart of a detection method of a color detection system for gold and silver card prints without color mark provided in an exemplary embodiment of the present invention;

[0040] Figure 5 The figure is a schematic diagram of a color difference calculation process provided in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In the description of the present invention, it should be noted that the directions or positional relationships indicated by "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are directions or positional relationships based on the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0043] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0045] See also Figure 1 , Figure 1 A color detection system for gold and silver card prints without color mark provided in an exemplary embodiment of the present invention is shown, comprising:

[0046] Printing material placement platform, used to place gold and silver cards to be tested;

[0047] Multi-spectrum dome light source, used to illuminate the gold and silver cards to be inspected;

[0048] A multispectral camera, used to capture images of gold and silver cards to be inspected under the illumination of a multispectral dome light source;

[0049] The image detection host is used to obtain the image of the gold and silver card to be detected taken by the multi-spectral camera and perform color detection;

[0050] Wherein, the multi-spectral camera and the multi-spectral dome light source are both translated relative to the printed matter placement platform.

[0051] Specifically, in this exemplary embodiment, the gold and silver cards to be tested are placed on the printed product placement platform, and the images of the gold and silver cards to be tested are photographed by a multispectral camera under the illumination of a multispectral dome light source, and finally the image detection host is used to perform color detection. Among them, the imaging process is based on the principle of linear array scanning imaging, which requires relative movement between the multispectral camera and the printed product placement platform. There are two common solutions: one is that the printed product placement platform is stationary, and the multispectral camera and the multispectral dome light source are translated relative to the printed product placement platform; the other is that the multispectral dome light source and the multispectral camera are stationary, and the printed product placement platform is translated; these two solutions are multiple implementation solutions of the basic imaging principle and do not affect the present invention.

[0052] Among them, light sources usually have strong directionality, and the energy of light sources in different directions is not equal. For common materials (such as white cardboard, which is mainly diffuse reflection), a 45 / 0 degree light path can be used. For the gold and silver cards in this exemplary embodiment, in order to ensure the accuracy of the uniform color of light in different directions, a dome light source is used to ensure the consistency of the light source in multiple directions.

[0053] The camera adopts a line scan camera, and the camera resolution is determined according to the resolution requirements of the photographed object. For example, a resolution of 7200 pixels can realize an image with a resolution of 254dpi for a format of 720mm. The scanning speed can be dynamically adjusted according to the scanning resolution requirements and the moving speed of the mechanical platform. The typical moving speed of the mechanical platform is 100mm / s. If the optical resolution is 254dpi, the scanning speed of the line scan camera is 1kHz. Under normal circumstances, the camera may be sensitive to red, green, and blue in terms of spectral resolution, or it may be sensitive to red, green, blue, black and white in terms of spectral resolution, or it may be multi-spectral imaging. In this exemplary embodiment, the color camera usually has the ability to acquire three RGB colors, and multi-spectral refers to the ability to acquire more than three spectra, which is a key factor in solving the measurement accuracy of color problems. There are many ways to obtain multispectral imaging, such as multispectral cameras and multispectral light sources. For example, a multispectral camera has a pixel structure that can sense multiple spectral bands at the same time, using broad-spectrum uniform white light as the illumination light source. A multispectral light source uses light sources with multiple bands, only lighting up some bands at each moment, and lighting them separately in multiple time periods, thereby realizing time division multiplexing and achieving multispectral imaging.

[0054] Furthermore, in this exemplary embodiment, a multi-spectral dome light source is used, and multi-spectral data can be obtained through a single scan, which can measure the color of high-gloss materials such as gold and silver cards, and can also solve the problem of reduced accuracy caused by the lack of spectrum in spot color measurement. At the same time, this imaging method is low-cost, thus solving the three problems of accuracy, efficiency and cost.

[0055] In a specific exemplary embodiment, the color detection system for color-markless gold and silver card prints in this exemplary embodiment is installed next to a printing host, which realizes online printing, and extracts real-time samples (gold and silver cards to be detected) from the printing host through manual or automatic mechanical means for detection.

[0056] More preferably, in an exemplary embodiment, the multi-spectrum dome light source includes a dome device and a plurality of groups of LED light strips located below the dome device, each group of LED light strips includes a plurality of groups of LED lamp beads with at least three different tones arranged in sequence.

[0057] Specifically, in this exemplary embodiment, Figure 2As shown, it is divided into four groups of LEDs. Since LEDs have the characteristics of high-speed switching and narrow spectrum, the time-division multiplexing technology based on multi-spectral light sources has the advantages of flexible and variable spectrum and low cost compared to multi-spectral cameras, and can solve the problem of spot color reproduction.

[0058] More preferably, in an exemplary embodiment, in each cycle, each LED lamp bead with different hue is lit separately according to the acquisition frequency of the multi-spectral camera.

[0059] Specifically, in this exemplary embodiment, the multi-spectral light source uses a light source of multiple bands, and only lights up some bands at each moment, which are divided into multiple time periods for lighting up separately, thereby realizing time division multiplexing and achieving multi-spectral imaging.

[0060] for Figure 2 There are 4 groups of LED lamp beads in different colors, such as Figure 3 As shown, it is divided into 4 moments t1-t4 and is lit separately, and the imaging camera uses four times the speed of conventional imaging. After collecting multiple images at different moments, the real multispectral image matching can be restored through image interpolation.

[0061] Multiple spectral responses at the nth moment,

[0062] Led1=Ledn1;

[0063] Led2=led(n-1)2*1 / 4+led(n)2*3 / 4;

[0064] Led3=led(n-1)3*1 / 2+led(n)3*1 / 2;

[0065] Led4=led(n-1)4*3 / 4+led(n)4*1 / 4;

[0066] According to the above formula, multiple spectra are matched to led1, thereby realizing four-spectrum acquisition. Similarly, more spectral information can be obtained by timing adjustment.

[0067] More preferably, in an exemplary embodiment, the printed matter placement platform absorbs and flattens the gold and silver cards to be tested by negative pressure adsorption.

[0068] See also Figure 4 , Figure 4 A detection method for a color detection system for a colorless gold and silver card print as provided in any of the above exemplary embodiments is provided, which is applied to an image detection host and includes the following steps:

[0069] For the gold and silver cards to be inspected, we first obtain the corresponding reference sample images, which are used as the color standard and spatial content standard.

[0070] Obtain real-time samples of gold and silver cards to be inspected that are actually captured by the multispectral camera;

[0071] Perform image registration processing on the real-time sample according to the image and text characteristics of the reference sample, and obtain pixel-level registration after processing;

[0072] Calculate the color difference between the reference sample and the real-time sample.

[0073] Specifically, the method in this exemplary embodiment is applied to an image detection host, which first obtains a reference sample image corresponding to the gold and silver cards to be detected (which can be obtained by real-time scanning or memory acquisition), then performs image acquisition on the real-time sample, and then calculates the color difference after the real-time sample and the reference sample are aligned.

[0074] Additionally, in a specific exemplary embodiment, when the color difference calculation fails, the ink key or the like may be adjusted.

[0075] The following exemplary embodiments will specifically describe the preferred embodiments of each step:

[0076] More preferably, in an exemplary embodiment, after obtaining the real-time sample of the gold and silver cards to be detected actually collected by the multi-spectral camera, the real-time sample is pre-processed:

[0077] Pixel-level noise is removed through noise reduction technology;

[0078] Achieve spatial white balance through a white standard plate to eliminate brightness errors caused by factors including light source and lens;

[0079] Perform multi-color correction to achieve color white balance;

[0080] Convert multispectral information into xyz space, and then into Lab space to achieve color correction;

[0081] Complete image preprocessing.

[0082] Specifically, in this exemplary embodiment, the corrected image will present the same effect as the color characteristics seen by the human eye.

[0083] More preferably, in an exemplary embodiment, the image registration process includes:

[0084] Based on the sub-images of the four corners of the reference sample, a global search is performed in the image of the real-time sample to find the overall positioning point, confirm the scaling factor, and remove irrelevant content larger than the reference image, including background information of the scanning device and information other than the finished product design content, to obtain a rough positioning matching image;

[0085] Fine position matching is performed based on the reference sample and the coarse positioning matching map, and pixel-level alignment is achieved after position matching.

[0086] Specifically, in this exemplary embodiment, through the first step of rough positioning and matching, fast four-corner positioning can be achieved, which can significantly speed up the matching process and reduce the failure rate of global matching that cannot find matching points.

[0087] More preferably, in an exemplary embodiment, the step of calculating the color difference between the reference sample and the real-time sample includes:

[0088] The color difference between each group of color blocks in the real-time sample and the corresponding color blocks in the reference sample is calculated, and the average color difference of each color block is calculated to globally evaluate the color difference.

[0089] Specifically, in this exemplary embodiment, the color difference calculation process is as follows: Figure 5 , the real-time sample obtains img1_Lab, and the color difference Img01_dE of the reference sample color block img0_Lab relative to the reference sample, and the average value Img01_dE_mean of each color block is compared with the average value spec01_dE_mean of the corresponding color block measured by the colorimeter, and the error dE_mean_error is not higher than the preset target value.

[0090] More preferably, in an exemplary embodiment, the color block is at least one color block of interest, and the average value of the color difference in the color block of interest is calculated, thereby globally evaluating the color difference; or:

[0091] The color blocks are weighted color blocks, and the color difference of each color block is multiplied by the corresponding weight to calculate the average value, so as to globally evaluate the color difference.

[0092] More preferably, in an exemplary embodiment, after obtaining the image of the corresponding reference sample, the reference sample is judged for smoothness characteristics: by searching for the maximum value Max and the minimum value min of the three components of RGB in the size range, the difference ColorDiff=max-min is calculated, and when the difference ColorDiff>the color difference threshold Th_ColorDiff, the image smooth_mask is set to 255, and if the difference ColorDiff≤the color difference threshold Th_ColorDiff is set to 0, a relatively smooth regional image smooth_mask is obtained;

[0093] When calculating the color difference between the reference sample and the real-time sample, when smooth_mask=255, the color difference is calculated, and when smooth_mask=0, the color difference is ignored.

[0094] Specifically, in this exemplary embodiment, there are usually uniform color areas and gradient color areas and sudden edge features in the original image. Although the above processing flow has image registration processing to achieve pixel-level registration accuracy, the printed product is based on gradient and edge features realized by different dot rates, which are not matched with the vector map of the original design manuscript and the three primary color image features obtained by scanning, and absolute alignment cannot be achieved, so there will be certain errors in such situations. Therefore, the color of the original image is smoothed to determine the features. Select parameter size: Fsize, color difference threshold parameter: Th_ColorDiff, search for the maximum Max and minimum min of the three components of image RGB within the size range of Fsize, and calculate the difference ColorDiff=max-min. When ColorDiff>Th_ColorDiff, set the image smooth_mask to 255. If ColorDiff≤Th_ColorDiff is set to 0, a relatively smooth regional image smooth_mask is obtained. When calling real-time image processing, when smooth_mask=255, calculate the color difference, and when smooth_mask=0, ignore the color difference.

[0095] Obviously, the above embodiments are merely examples for clear explanation, and are not intended to limit the implementation methods. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. A color detection system for printed gold and silver cards without color mark, characterized by: include: Printing material placement platform, used to place gold and silver cards to be tested; Multi-spectrum dome light source, used to illuminate the gold and silver cards to be inspected; A multispectral camera, used to capture images of gold and silver cards to be inspected under the illumination of a multispectral dome light source; Image detection host, used to obtain the image of the gold and silver card to be detected taken by the multi-spectral camera and perform color detection; Wherein, the multi-spectral camera and the multi-spectral dome light source are both translated relative to the printed matter placement platform.

2. The color detection system for colorless gold and silver card prints according to claim 1, characterized in that: The multi-spectrum dome light source includes a dome device and a plurality of groups of LED light strips located below the dome device, and each group of LED light strips includes a plurality of groups of LED lamp beads with at least three different tones arranged in sequence.

3. The color detection system for colorless gold and silver card prints according to claim 2, characterized in that: In each cycle, each LED lamp bead with different hue is lit up according to the acquisition frequency of the multi-spectral camera.

4. The color detection system for colorless gold and silver card prints according to claim 1, characterized in that: The printed matter placing platform absorbs and flattens the gold and silver cards to be tested by negative pressure adsorption.

5. The detection method of the color detection system of the gold and silver card printing without color mark as claimed in any one of claims 1 to 4, applied to an image detection host, characterized in that: The following steps are involved: For the gold and silver cards to be inspected, we first obtain the corresponding reference sample images, which are used as the color standard and spatial content standard. Obtain real-time samples of gold and silver cards to be inspected that are actually captured by the multispectral camera; Perform image registration processing on the real-time sample according to the image and text characteristics of the reference sample, and obtain pixel-level registration after processing; Calculate the color difference between the reference sample and the real-time sample.

6. The detection method of the color detection system for colorless gold and silver card printing according to claim 5, characterized in that: After obtaining the real-time samples of the gold and silver cards to be detected actually collected by the multispectral camera, pre-process the real-time samples: Pixel-level noise is removed through noise reduction technology; Achieve spatial white balance through a white standard plate to eliminate brightness errors caused by factors including light source and lens; Perform multi-color correction to achieve color white balance; The multispectral information is converted into xyz space and then converted into Lab space to achieve color correction.

7. The detection method of a color detection system for colorless gold and silver card prints according to claim 5, characterized in that: The image registration process comprises: Based on the sub-images of the four corners of the reference sample, a global search is performed in the image of the real-time sample to find the overall positioning point, confirm the scaling factor, and remove irrelevant content larger than the reference image, including background information of the scanning device and information other than the finished product design content, to obtain a rough positioning matching image; Fine position matching is performed based on the reference sample and the coarse positioning matching map, and pixel-level alignment is achieved after position matching.

8. The detection method of the color detection system for colorless gold and silver card prints according to claim 5, characterized in that: The color difference calculation of the reference sample and the real-time sample includes: The color difference between each group of color blocks in the real-time sample and the corresponding color blocks in the reference sample is calculated, and the average color difference of each color block is calculated to globally evaluate the color difference.

9. The detection method of the color detection system of the gold and silver card printed matter without color mark according to claim 8 is characterized by: The color block is at least one color block of interest, and the average value of the color difference in the color block of interest is calculated, thereby globally evaluating the color difference; or: The color blocks are weighted color blocks, and the color difference of each color block is multiplied by the corresponding weight to calculate the average value, so as to globally evaluate the color difference.

10. The detection method of a color detection system for colorless gold and silver card prints according to claim 5, characterized in that: After obtaining the image of the corresponding reference sample, the smooth feature of the reference sample is judged: by searching the maximum value Max and the minimum value min of the three components of the image RGB within the size range, the difference ColorDiff = max-min is calculated, and when the difference ColorDiff> the color difference threshold Th_ColorDiff, the image smooth_mask is set to 255, if the difference ColorDiff≤the color difference threshold Th_ColorDiff is set to 0, and a relatively smooth area image smooth_mask is obtained; When calculating the color difference between the reference sample and the real-time sample, when smooth_mask=255, the color difference is calculated, and when smooth_mask=0, the color difference is ignored.

Images