Offset printing off-line detection system based on machine vision
Through the offline offset printing detection system based on machine vision, the problems of traditional manual inspection accuracy and low efficiency are solved, high-precision and rapid printing defect detection and real-time monitoring are achieved, and the efficiency and data support capabilities of printing quality control are improved.
Patent Information
- Application Number
- CN202411081689.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional manual quality inspection is difficult to meet the high requirements of printing quality, has low detection accuracy and efficiency, and it is difficult to monitor the printing process in real time and provide data support.
Design an offline offset printing detection system based on machine vision, including acquisition, processing, analysis, judgment and execution units, photograph printed objects through high-speed linear array color cameras and light sources, transcode them into TIFF format, compare and adjust, and detect printing defects And adjust the printing parameters in real time.
It realizes pixel-level detection accuracy, quickly detects printing defects, supports multiple types of files, can monitor color changes in real time, improves detection efficiency and data support capabilities, and has high cost-effectiveness.
Smart Images

Figure CN119086544A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of printing, and in particular to an offset printing offline detection system based on machine vision. Background Art
[0002] The intelligence of equipment is an important part of intelligent manufacturing, and the intelligence of quality control system is an indispensable part of it. The traditional way of completing quality inspection by hand is far from meeting the high requirements for printing quality. With the rapid development of machine vision, a comprehensive technology in China, the advantages of visual inspection systems that equip equipment with brains and eyes are particularly prominent. The inspection accuracy and efficiency have been greatly improved. The inspection data can be displayed in real time, and data analysis, archiving and sharing can also be performed. This not only monitors the quality of printed products in real time during the printing process, but also provides big data support for enterprise management. Summary of the invention
[0003] In view of the shortcomings of the prior art, the present invention solves the technical problems by adopting a technical solution: an offset printing offline detection system based on machine vision, comprising: A collection unit, the collection unit is used to input printing information into the system; A processing unit, the processing unit is used to receive the data information output from the acquisition unit and convert the received data information into a format that can be recognized by the printing press; An analysis unit, the analysis unit is used to receive the data information output from the processing unit, retrieve the corresponding initial information, and compare the received data information with the corresponding initial information to obtain comparison information; A judging unit, which is used to judge whether the printing effect of the printer meets the requirements; The execution unit is used to adjust the unqualified printing information and execute the printing operation at the same time.
[0004] Preferably, the acquisition unit is electrically connected to the processing unit via a cable, the processing unit is electrically connected to the analysis unit via a wire, the analysis unit is electrically connected to the judgment unit via a wire, and the judgment unit is electrically connected to the execution unit via a cable.
[0005] Preferably, the collection unit includes an input module and a sampling module, wherein: The input module is used to take photos and samples of external objects that need to be printed through a high-speed linear array color camera, light source and power supply; The sampling module is used to randomly select printed products from the printed batch print files and perform entry operations on the selected products.
[0006] Preferably, the processing unit comprises a transcoding module, which converts the printing information in different formats received from the acquisition module into a unified TIFF format.
[0007] Preferably, the analysis unit comprises a storage module, and the storage module is used to store the original sample in the system.
[0008] Preferably, the contents judged by the judgment unit include missing printing, incomplete characters, dirty spots, burrs, foreign matter, smudges, lines, ink flakes, color difference, paper fibers, overprinting, missing prints, dirty spots, white lines, overprinting deviation, scratches, patterns, bumps, white spots and wrinkles.
[0009] Preferably, the execution unit includes an ink color adjustment module, a flattening module and a display module, wherein: The ink color adjustment module is used to adjust the printing color until the printing requirements are met; The flattening module flattens the printed document through a flattening plate to display the details of the printed document; The display module uses a display to digitally display the printed image The beneficial effects of the present invention are as follows: The present invention can be applied to the detection of commercially printed flat sheets and roll papers such as books, teaching aids, instructions, medicine packages, cigarette packages, and color boxes. The present invention has pixel-level detection accuracy, a minimum detection of 15DN, and a detection time of less than 30 seconds for products with a width of 1020 mm. The present invention supports modeling of multiple types of electronic files, and can detect various printing defects such as waste plates, waste files, missing radicals, punctuation marks, wrong characters, missing characters, ink spots, white spots, dirty spots, and oil stains. It can detect color differences and monitor color changes in the form of color difference histogram display. It can detect and browse multiple machines at the same time, and has a high cost-effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 is a system block diagram of the present invention; Figure 2 It is the front-stage process flow chart of the present invention; Figure 3 It is a detection flow chart of the present invention; Figure 4 This is the first detection sample calibration flow chart of the present invention. DETAILED DESCRIPTION
[0011] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses. Example
[0012] After the source file is produced before printing, the ONE BIT TIF file will be published, and then the CTP plate will be placed on the printing press for printing. Figure 2 ; In order to ensure that there is no mass waste or serious waste of printing during the printing process, the conventional means are: Manual first proofreading; Captain diligent sampling; QC diligent sampling proofreading; The above-mentioned control measures are all based on the premise of people's positive initiative. Since printing is a fast-paced, tight-task, and high-pressure job, it requires people to have strong stress resistance and other factors. In the long run, it is bound to be difficult to guarantee. The application of offset printing offline detection system can control from the source, eliminate human errors, eliminate batch waste, and eliminate serious waste.
[0013] See also Figure 1 - Figure 4 The present invention provides a technical solution: an offset printing offline detection system based on machine vision, comprising: A collection unit, the collection unit is used to input printing information into the system; A processing unit, the processing unit is used to receive the data information output from the acquisition unit and convert the received data information into a format that can be recognized by the printing press; An analysis unit, the analysis unit is used to receive the data information output from the processing unit, retrieve the corresponding initial information, and compare the received data information with the corresponding initial information to obtain comparison information; A judging unit, which is used to judge whether the printing effect of the printer meets the requirements; The execution unit is used to adjust the unqualified printing information and execute the printing operation at the same time.
[0014] The collection unit is electrically connected to the processing unit through a cable, the processing unit is electrically connected to the analysis unit through a wire, the analysis unit is electrically connected to the judgment unit through a wire, and the judgment unit is electrically connected to the execution unit through a cable.
[0015] The collection unit includes an input module and a sampling module, wherein: The input module is used to take photos and samples of external objects that need to be printed through a high-speed linear array color camera, light source and power supply; The sampling module is used to randomly select printed products from the printed batch print files and perform entry operations on the selected products.
[0016] The processing unit comprises a transcoding module, which converts the printing information in different formats received from the acquisition module into a unified TIFF format.
[0017] The analysis unit comprises a storage module, and the storage module is used for storing the original sample into the system.
[0018] The judgment unit judges the following contents: missing printing, incomplete characters, dirty spots, burrs, foreign matter, smudges, lines, ink flakes, color difference, paper fibers, overprinting, missing printing, dirty spots, white lines, overprinting deviation, scratches, patterns, bumps, white spots and wrinkles.
[0019] The execution unit includes an ink color adjustment module, a flattening module and a display module, wherein: The ink color adjustment module is used to adjust the printing color until the printing requirements are met; The flattening module flattens the printed document through a flattening plate to display the details of the printed document; The display module uses a display to digitally display the printed image.
[0020] When using it, you must first have the original sample as the basis for mass production. With the assistance of power and light source, the high-speed linear array color camera shoots the object to be printed. The captured image is collected by the acquisition unit through the input module, and then the processing unit uniformly transcodes the printing information received from the acquisition unit into TIFF format through the transcoding module. Because the TIFF format has the advantage of high clarity, it is possible to clearly see the defects during printing, complete the CTP plate, and then the printing machine performs proofing confirmation. The proofed print is manually compared with the actual object. After the ink color is adjusted and multiple proofing adjustments are made, until the minimum error is approached, the sample at this time is used as the original sample and stored inside the printing machine system.
[0021] Subsequently, the printing press carries out batch printing based on the original sample. During the batch printing process, the analysis unit retrieves the printing data of the original sample from its internal storage module and compares it through the judgment unit. If the judgment unit finds that the printed materials randomly sampled in the batch printing have any of the following conditions: missing prints, incomplete characters, dirty spots, burrs, foreign matter, smudges, pulling lines, ink skin, color difference, paper hair, overprinting, missing prints, dirty spots, white lines, overprint deviation, scratches, patterns, bumps, white spots and wrinkles, then the printed materials are unqualified. Otherwise, they are qualified. When it is judged to be unqualified, the ink color adjustment module, flattening module and display module in the execution module adjust the unqualified printed materials through the printing press, flattening plate and display, and then feed back to the acquisition unit for secondary inspection until the judgment unit judges them to be qualified.
[0022] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.
Claims
1. An offset printing offline detection system based on machine vision, characterized in that: include: A collection unit, the collection unit is used to enter the printing information into the system; A processing unit, the processing unit is used to receive the data information output from the acquisition unit and convert the received data information into a format that can be recognized by the printing press; An analysis unit, the analysis unit is used to receive the data information output from the processing unit, retrieve the corresponding initial information, and compare the received data information with the corresponding initial information to obtain comparison information; A judging unit, the judging unit is used to judge whether the printing effect of the printer meets the requirements; An execution unit is used to adjust unqualified printing information and execute a printing operation at the same time.
2. The machine vision-based offset printing offline detection system according to claim 1, characterized in that: The acquisition unit is electrically connected to the processing unit through a cable, the processing unit is electrically connected to the analysis unit through a wire, the analysis unit is electrically connected to the judgment unit through a wire, and the judgment unit is electrically connected to the execution unit through a cable.
3. The machine vision-based offset printing offline detection system according to claim 1, characterized in that: The acquisition unit includes an input module and a sampling module, wherein: The input module is used to take photos and samples of external objects that need to be printed through a high-speed linear array color camera, a light source and a power supply; The sampling module is used to randomly select printed products from the printed batch print files and perform entry operations on the selected products.
4. The machine vision-based offset printing offline detection system according to claim 1, characterized in that: The processing unit comprises a transcoding module, which converts the printing information in different formats received from the acquisition module into a unified TIFF format.
5. The machine vision-based offset printing offline detection system according to claim 1, characterized in that: The analysis unit comprises a storage module, and the storage module is used to store the original sample in the system.
6. The machine vision-based offset printing offline detection system according to claim 1, characterized in that: The contents judged by the judgment unit include missing printing, incomplete characters, dirty spots, burrs, foreign matter, smudges, lines, ink flakes, color difference, paper fibers, overprinting, missing printing, dirty spots, white lines, overprinting deviation, scratches, patterns, bumps, white spots and wrinkles.
7. The machine vision-based offset printing offline detection system according to claim 1, characterized in that: The execution unit includes an ink color adjustment module, a flattening module and a display module, wherein: The ink color adjustment module is used to adjust the printed color until the printing requirements are met; The flattening module flattens the printed document by means of a flattening plate to display the details of the printed document; The display module uses a display to digitally display the printed image.
