![<?echo $_SERVER['SERVER_NAME'];?>](/template/twentyseventeen/skin/images/header.jpg)
The printing process is often interfered by various factors such as temperature, humidity, machine accuracy, and equipment operation, and the printing quality cannot reach the established requirements. This requires the inspection and control of the entire printing process. Printed products often have such defects. The common print defects are missing prints, flying inks, color casts, black spots, scratches, misprints, and so on. However, since people are limited by their own conditions and cannot complete real-time monitoring, it is very important to establish an effective automatic print quality inspection technology. This article takes this as the research object, and studies the development status of the automatic detection system at home and abroad and the basic composition of the automatic detection system.
1. Two core issues affecting printing quality and the necessity and feasibility of automatic detection technology
Summarizing the most commonly occurring printing quality problems in printing can be divided into two major categories: printing color problems and printing defect problems. The printing color problem is mainly manifested as color cast, and the printing defect problem mainly represents shape defects.
Offset presses used in color printing usually have monochrome offset presses, two-color offset presses, and four-color offset presses. There are three main reasons for the color cast: First, the general principle of printing a color cover with a two-color offset press. When using a two-color offset printing machine to print a color cover, the two colors printed at the same time are wet and wet, and the two colors printed later. The printing is wet-stacked with respect to the first two colors. Second, the general principle of printing color covers for four-color offset printing machines, when using four-color printing presses to print color covers, because it is a wet and wet printing, which increases the difficulty in the printing process, requiring four colors of ink The density after overprinting should be small, and the thickness of each ink layer should be thin, otherwise there will be back stains or other printing accidents. Third, the relationship between ink viscosity and color, ink viscosity refers to the size of the cohesion of the ink or the size of the resistance generated when the ink layer breaks. In multi-color printing, we must follow the printing order of the ink viscosity from big to small. Printing, that is, the ink viscosity of the previous color is greater than the ink viscosity of the latter color, so as to ensure normal overprint of the ink.
According to the analysis of the influencing factors of print quality, it is known that the defects are generally shape defects. It focuses on shape features such as line shape defects. Among the most available image quality tests, there are some metrics that are suitable for evaluating image quality. These tests include: point quality, line quality, text quality, over-range spraying, and spatial resolution. The common print defects are: flying ink, pinholes, missing prints, black spots, scratches, misprints, etc. The detection of these defects is currently widely used as a manual visual inspection method. It is labor-intensive, time-consuming and labor-intensive, and the testing standards are not uniform. In particular, with the increase in printing speed, it has gradually failed to meet the demand for production. Therefore, the automatic detection of print defects has gradually become the industry trend.
In order to increase production efficiency, the online intelligent detection technology introduces a printing process. The basic principles are as follows: The system passes the CCD camera lens, collects the non-defective print product as a standard image, and then collects the to-be-checked image on the printing production line. Each frame will be collected. The to-be-checked image is transmitted to the scene for comparison and analysis with the standard image to find the image with quality problems, thereby discovering the quality problem of the print product corresponding to the frame image, and finally automatically adjusting the on-line control of the quality of the corresponding printing department. In the specific implementation of the on-line inspection of printed products, it is generally divided into two steps: first, preparation for testing, that is, image acquisition of qualified products to obtain standard printed image. Followed by the actual detection, the image of the printed matter to be examined is compared with the standard template, so that the presence or absence of the defect and the position of the defect are determined according to the comparison result, and the defect information is recorded. The following is the current status of research in various countries and the analysis of their system components.
2. Current status of automatic detection technologies for printed matter at home and abroad
The automatic detection technology for printing image quality started in the 1980s and 1990s. In 1990, Katsuyuki Tanimizu of Tokyo, Japan conducted an automatic quality inspection study in the printing industry, and provided an index space method for automatically detecting print surface defects. X and Y indicate the position coordinates of each pixel. The Z-axis represents the gray values ​​of the image points, and a space coordinate system is established so that each image point can find its corresponding position in this coordinate system. The gray level of the position of the template image and the image to be checked is compared in the coordinate system. The degree value determines whether there is a defect point in the image to be checked. The image processing process and the detection process of this method are independent from each other and can detect more complicated images. However, its algorithm is more complex and there are many inconveniences in application.
In 1993, France's B. Mehenni also conducted research on this topic. He proposed a method that combines the n-tupe method and the pixel-by-pixel comparison method. This method has the characteristics of high speed, high parameter output, but it requires specialized hardware equipment. At the same time, the task of automatic quality inspection can only be accomplished through teaching.
In 1998, some scholars successively introduced the Gabor filter method into the quality inspection of printed images. This method can detect a variety of image defects and has a certain degree of adaptability. It is suitable for the detection of big data systems, but the abor method There is a big drawback, and the recognition speed is slow because its good recognition is based on exact matching, which greatly increases the complexity of the operation and reduces its practicality.
In 2003, J. Luo and Z. Zhang of the University of Exeter in the United Kingdom proposed a color print detection algorithm based on image processing technology. The algorithm first carries out illumination correction, then gives a color three-dimensional histogram, features extraction, and finally uses neural networks to classify images and identify qualified images.
At present, many foreign manufacturers have developed a variety of printed automatic quality inspection system. For example, the printing quality inspection system developed by Vision Experts of Germany can detect printing errors on the surface of various papers and various materials online. The GED NOTA-SAVE series of high-precision print quality inspection systems manufactured by Germany's ELTROMAT company has been used in the quality inspection process for banknote printing. Practice has proved that they greatly shorten the time of detection, improve the detection speed, and achieve the purpose of monitoring the production process of high-precision prints. Israel's AVT company has also produced PrintVision series products for detecting print quality, which can detect printing errors such as color difference, missed print, streaks and spots.
At the actual application level, the major researches in this field in the world are Japan and Germany. Companies such as FUTEC in Japan and TOKIMEC Co., Ltd. in Japan have the EasyMax series and the Print-Pac system, and the Print-Expert 4000 OCV/2 system developed by Vision-Experts of Germany. In addition, there are companies such as Switzerland's BOBST and America's PROIMAGE that can provide automatic print quality inspection equipment.
3 online detection system composition
In order to solve the problem of automatic defect detection in the printing process, an on-line detection system can be designed according to the characteristics of the printing defect, which mainly includes four parts of image acquisition, positioning, detection and result output. The image acquisition consists of CCD, lens, light source, and video image. The acquisition card and computer components are mainly used to complete the image noise removal, geometric transformation and positioning determination through software programming. The image detection system mainly uses the binary image to carry out the automatic detection process of the printed products, and the output is mainly calculated by the data conversion part. The resulting data is output, and the display of the printing feature amount, such as the ink amount display. When a full-screen printing quality inspection system was established, the CCD camera was used to continuously photograph the printed matter, and each captured image was transmitted to the on-site computer. Through the image processing software, the image information was analyzed and processed to find the quality. The image of the problem gives the quality problem of the print corresponding to the image, and then the information is fed back to the operator via the transmission line or directly fed back to the printer for adjustment. This will not only reduce the labor intensity of workers, but will also reduce the defective products and increase production efficiency.
The hardware part of the on-line inspection system for print defects is shown in Fig. 1. It is mainly composed of a CCD, a lens, an image acquisition card, a computer, and a display system.
First, CCDs, lenses, light sources, and image capture cards work together to capture and digitize images. High-quality image information is the original basis for the correct judgment and decision of the system, and is the key to the success of the entire system. CCD devices can be divided into two major categories: line array and area array. The linear array CCD can only obtain one line of information of an image at a time. The object to be photographed must be moved in a straight line from the camera to obtain a complete image. Therefore, it is very suitable for image detection of an object moving at a constant speed and at a uniform speed. The area array CCD can obtain the entire image information once. In the full-screen detection system, a Bayer-converted area-array CCD from Sony Corporation was used.
After the experiment, for a small-format print (200mm×200mm), when the distance between the print and the lens is 15mm, the illumination of the light source is the most uniform and the image quality is good. Therefore choose lens focal length 3.5-8mm, imaging size is 1/3 inch, aperture is F1.4. The light source adopts forward vertical lighting.
Again, the task of the image acquisition module is mainly to complete the control of the real-time display of the captured image to the screen. The acquisition mode is divided into single frame acquisition and real-time acquisition and display. In the full-screen printing quality inspection system, after the binarization of the captured image is important, the analysis of the image data is a more complicated process. Therefore, after the image captured in a single frame is stored in a specified position, Use an image pointer to call the image for processing.
Finally, the output system mainly completes the output of the results and adjusts the printing process according to the output data, including operations such as pause, reprint, and overlay.
4. The main hardware features
1CCD camera. CCD (Change Coupled Device) is a new semiconductor optoelectronic imaging device developed in the 1970s. It is a special-purpose chip that utilizes the photoelectric effect principle to achieve image ingestion. There are two types of CCDs, wired and planar, both of which require an optical imaging system to image the subject image on the CCD. The electrical imaging device is a special-purpose chip that utilizes the photoelectric effect principle to achieve image ingestion. Here we choose an area array CCD, which arranges the one-dimensional linear array CCD photosensitive cells and displacement integrators into a two-dimensional array in a certain way. For the selected CCD camera, it is necessary to focus on six parameters: color, resolution, minimum illumination, CCD chip size, Exposure, and Shutter.
2 optical lens. The lens is equivalent to the lens of the human eye. If there is no lens, no object can be seen by the human eye. If there is no lens, then the image output by the camera is a white one, there is no clear image output. When the camera shoots an image, if the image becomes unclear, you can adjust the camera's back focus, change the distance between the CCD chip and the lens reference plane, and make the blurred image clear.
3 image capture card. The image capture card is responsible for converting analog video signals captured by the camera into digital image signals for processing by the computer. Usually the image capture card occupies a slot in the PC bus and has an external CCD camera, image monitor, and video signal interface. The image acquisition card together with the camera, monitor, and PC form the basic hardware environment of a typical microcomputer image processing system. After the signal enters the image capture card, it is divided into two channels. One line is divided into two rows by the synchronous separator and the field synchronization signal is sent to the phase detector to maintain the same phase relationship with the line and field synchronization signals generated by the card timing generator. The control circuit allows the units on the card to work synchronously according to the video signal line and field television system requirements. Another video signal passes through a pre-processing circuit. The gray signal of the video is amplified from the standard TV signal with a peak value of 1V to the amplitude required by the A/D converter, and the level and contrast are adjusted. The signal output by the preprocessing circuit is converted into a digital signal by an A/D converter. The timing controller stores the digital signal in the frame memory. At the same time, a full TV signal output unit provided for the analog monitor is set on the card. It consists of a lookup table, a D/A converter, and a synchronous synthesis circuit. The lookup table puts the address of the same gray value in the digital image output by the A/D converter into the specified space under the control of the microcomputer interface circuit. These data are converted into analog voltage values ​​by D/A, so that the output of the D/A converter is in the gray level of the specified row in the look-up table, and the image can be quickly restored to the video monitor. Under the influence of software, the image card can easily store, detect and add, subtract, etc. digital images. There are many kinds of image capture cards. According to different classification methods, there are black and white images and color image capture cards, analog signals and digital signal acquisition cards, and composite signal and RGB component signal input capture cards. When choosing the image acquisition card, the factors such as the functional requirements of the system, the acquisition accuracy of the image, and the match of the output signal of the camera should be taken into consideration.
1. Two core issues affecting printing quality and the necessity and feasibility of automatic detection technology
Summarizing the most commonly occurring printing quality problems in printing can be divided into two major categories: printing color problems and printing defect problems. The printing color problem is mainly manifested as color cast, and the printing defect problem mainly represents shape defects.
Offset presses used in color printing usually have monochrome offset presses, two-color offset presses, and four-color offset presses. There are three main reasons for the color cast: First, the general principle of printing a color cover with a two-color offset press. When using a two-color offset printing machine to print a color cover, the two colors printed at the same time are wet and wet, and the two colors printed later. The printing is wet-stacked with respect to the first two colors. Second, the general principle of printing color covers for four-color offset printing machines, when using four-color printing presses to print color covers, because it is a wet and wet printing, which increases the difficulty in the printing process, requiring four colors of ink The density after overprinting should be small, and the thickness of each ink layer should be thin, otherwise there will be back stains or other printing accidents. Third, the relationship between ink viscosity and color, ink viscosity refers to the size of the cohesion of the ink or the size of the resistance generated when the ink layer breaks. In multi-color printing, we must follow the printing order of the ink viscosity from big to small. Printing, that is, the ink viscosity of the previous color is greater than the ink viscosity of the latter color, so as to ensure normal overprint of the ink.
According to the analysis of the influencing factors of print quality, it is known that the defects are generally shape defects. It focuses on shape features such as line shape defects. Among the most available image quality tests, there are some metrics that are suitable for evaluating image quality. These tests include: point quality, line quality, text quality, over-range spraying, and spatial resolution. The common print defects are: flying ink, pinholes, missing prints, black spots, scratches, misprints, etc. The detection of these defects is currently widely used as a manual visual inspection method. It is labor-intensive, time-consuming and labor-intensive, and the testing standards are not uniform. In particular, with the increase in printing speed, it has gradually failed to meet the demand for production. Therefore, the automatic detection of print defects has gradually become the industry trend.
In order to increase production efficiency, the online intelligent detection technology introduces a printing process. The basic principles are as follows: The system passes the CCD camera lens, collects the non-defective print product as a standard image, and then collects the to-be-checked image on the printing production line. Each frame will be collected. The to-be-checked image is transmitted to the scene for comparison and analysis with the standard image to find the image with quality problems, thereby discovering the quality problem of the print product corresponding to the frame image, and finally automatically adjusting the on-line control of the quality of the corresponding printing department. In the specific implementation of the on-line inspection of printed products, it is generally divided into two steps: first, preparation for testing, that is, image acquisition of qualified products to obtain standard printed image. Followed by the actual detection, the image of the printed matter to be examined is compared with the standard template, so that the presence or absence of the defect and the position of the defect are determined according to the comparison result, and the defect information is recorded. The following is the current status of research in various countries and the analysis of their system components.
2. Current status of automatic detection technologies for printed matter at home and abroad
The automatic detection technology for printing image quality started in the 1980s and 1990s. In 1990, Katsuyuki Tanimizu of Tokyo, Japan conducted an automatic quality inspection study in the printing industry, and provided an index space method for automatically detecting print surface defects. X and Y indicate the position coordinates of each pixel. The Z-axis represents the gray values ​​of the image points, and a space coordinate system is established so that each image point can find its corresponding position in this coordinate system. The gray level of the position of the template image and the image to be checked is compared in the coordinate system. The degree value determines whether there is a defect point in the image to be checked. The image processing process and the detection process of this method are independent from each other and can detect more complicated images. However, its algorithm is more complex and there are many inconveniences in application.
In 1993, France's B. Mehenni also conducted research on this topic. He proposed a method that combines the n-tupe method and the pixel-by-pixel comparison method. This method has the characteristics of high speed, high parameter output, but it requires specialized hardware equipment. At the same time, the task of automatic quality inspection can only be accomplished through teaching.
In 1998, some scholars successively introduced the Gabor filter method into the quality inspection of printed images. This method can detect a variety of image defects and has a certain degree of adaptability. It is suitable for the detection of big data systems, but the abor method There is a big drawback, and the recognition speed is slow because its good recognition is based on exact matching, which greatly increases the complexity of the operation and reduces its practicality.
In 2003, J. Luo and Z. Zhang of the University of Exeter in the United Kingdom proposed a color print detection algorithm based on image processing technology. The algorithm first carries out illumination correction, then gives a color three-dimensional histogram, features extraction, and finally uses neural networks to classify images and identify qualified images.
At present, many foreign manufacturers have developed a variety of printed automatic quality inspection system. For example, the printing quality inspection system developed by Vision Experts of Germany can detect printing errors on the surface of various papers and various materials online. The GED NOTA-SAVE series of high-precision print quality inspection systems manufactured by Germany's ELTROMAT company has been used in the quality inspection process for banknote printing. Practice has proved that they greatly shorten the time of detection, improve the detection speed, and achieve the purpose of monitoring the production process of high-precision prints. Israel's AVT company has also produced PrintVision series products for detecting print quality, which can detect printing errors such as color difference, missed print, streaks and spots.
At the actual application level, the major researches in this field in the world are Japan and Germany. Companies such as FUTEC in Japan and TOKIMEC Co., Ltd. in Japan have the EasyMax series and the Print-Pac system, and the Print-Expert 4000 OCV/2 system developed by Vision-Experts of Germany. In addition, there are companies such as Switzerland's BOBST and America's PROIMAGE that can provide automatic print quality inspection equipment.
3 online detection system composition
In order to solve the problem of automatic defect detection in the printing process, an on-line detection system can be designed according to the characteristics of the printing defect, which mainly includes four parts of image acquisition, positioning, detection and result output. The image acquisition consists of CCD, lens, light source, and video image. The acquisition card and computer components are mainly used to complete the image noise removal, geometric transformation and positioning determination through software programming. The image detection system mainly uses the binary image to carry out the automatic detection process of the printed products, and the output is mainly calculated by the data conversion part. The resulting data is output, and the display of the printing feature amount, such as the ink amount display. When a full-screen printing quality inspection system was established, the CCD camera was used to continuously photograph the printed matter, and each captured image was transmitted to the on-site computer. Through the image processing software, the image information was analyzed and processed to find the quality. The image of the problem gives the quality problem of the print corresponding to the image, and then the information is fed back to the operator via the transmission line or directly fed back to the printer for adjustment. This will not only reduce the labor intensity of workers, but will also reduce the defective products and increase production efficiency.
The hardware part of the on-line inspection system for print defects is shown in Fig. 1. It is mainly composed of a CCD, a lens, an image acquisition card, a computer, and a display system.
First, CCDs, lenses, light sources, and image capture cards work together to capture and digitize images. High-quality image information is the original basis for the correct judgment and decision of the system, and is the key to the success of the entire system. CCD devices can be divided into two major categories: line array and area array. The linear array CCD can only obtain one line of information of an image at a time. The object to be photographed must be moved in a straight line from the camera to obtain a complete image. Therefore, it is very suitable for image detection of an object moving at a constant speed and at a uniform speed. The area array CCD can obtain the entire image information once. In the full-screen detection system, a Bayer-converted area-array CCD from Sony Corporation was used.
After the experiment, for a small-format print (200mm×200mm), when the distance between the print and the lens is 15mm, the illumination of the light source is the most uniform and the image quality is good. Therefore choose lens focal length 3.5-8mm, imaging size is 1/3 inch, aperture is F1.4. The light source adopts forward vertical lighting.
Again, the task of the image acquisition module is mainly to complete the control of the real-time display of the captured image to the screen. The acquisition mode is divided into single frame acquisition and real-time acquisition and display. In the full-screen printing quality inspection system, after the binarization of the captured image is important, the analysis of the image data is a more complicated process. Therefore, after the image captured in a single frame is stored in a specified position, Use an image pointer to call the image for processing.
Finally, the output system mainly completes the output of the results and adjusts the printing process according to the output data, including operations such as pause, reprint, and overlay.
4. The main hardware features
1CCD camera. CCD (Change Coupled Device) is a new semiconductor optoelectronic imaging device developed in the 1970s. It is a special-purpose chip that utilizes the photoelectric effect principle to achieve image ingestion. There are two types of CCDs, wired and planar, both of which require an optical imaging system to image the subject image on the CCD. The electrical imaging device is a special-purpose chip that utilizes the photoelectric effect principle to achieve image ingestion. Here we choose an area array CCD, which arranges the one-dimensional linear array CCD photosensitive cells and displacement integrators into a two-dimensional array in a certain way. For the selected CCD camera, it is necessary to focus on six parameters: color, resolution, minimum illumination, CCD chip size, Exposure, and Shutter.
2 optical lens. The lens is equivalent to the lens of the human eye. If there is no lens, no object can be seen by the human eye. If there is no lens, then the image output by the camera is a white one, there is no clear image output. When the camera shoots an image, if the image becomes unclear, you can adjust the camera's back focus, change the distance between the CCD chip and the lens reference plane, and make the blurred image clear.
3 image capture card. The image capture card is responsible for converting analog video signals captured by the camera into digital image signals for processing by the computer. Usually the image capture card occupies a slot in the PC bus and has an external CCD camera, image monitor, and video signal interface. The image acquisition card together with the camera, monitor, and PC form the basic hardware environment of a typical microcomputer image processing system. After the signal enters the image capture card, it is divided into two channels. One line is divided into two rows by the synchronous separator and the field synchronization signal is sent to the phase detector to maintain the same phase relationship with the line and field synchronization signals generated by the card timing generator. The control circuit allows the units on the card to work synchronously according to the video signal line and field television system requirements. Another video signal passes through a pre-processing circuit. The gray signal of the video is amplified from the standard TV signal with a peak value of 1V to the amplitude required by the A/D converter, and the level and contrast are adjusted. The signal output by the preprocessing circuit is converted into a digital signal by an A/D converter. The timing controller stores the digital signal in the frame memory. At the same time, a full TV signal output unit provided for the analog monitor is set on the card. It consists of a lookup table, a D/A converter, and a synchronous synthesis circuit. The lookup table puts the address of the same gray value in the digital image output by the A/D converter into the specified space under the control of the microcomputer interface circuit. These data are converted into analog voltage values ​​by D/A, so that the output of the D/A converter is in the gray level of the specified row in the look-up table, and the image can be quickly restored to the video monitor. Under the influence of software, the image card can easily store, detect and add, subtract, etc. digital images. There are many kinds of image capture cards. According to different classification methods, there are black and white images and color image capture cards, analog signals and digital signal acquisition cards, and composite signal and RGB component signal input capture cards. When choosing the image acquisition card, the factors such as the functional requirements of the system, the acquisition accuracy of the image, and the match of the output signal of the camera should be taken into consideration.
Food Sachet,Plastic Doypack,Doypack With Spout,Doypack With Zipper
Guangdong Danqing Printing Co., Ltd. , https://www.spoutpouchfactory.com