CN113436196B - Two-dimensional code film production management system based on image recognition technology - Google Patents

Two-dimensional code film production management system based on image recognition technology Download PDF

Info

Publication number
CN113436196B
CN113436196B CN202110992843.4A CN202110992843A CN113436196B CN 113436196 B CN113436196 B CN 113436196B CN 202110992843 A CN202110992843 A CN 202110992843A CN 113436196 B CN113436196 B CN 113436196B
Authority
CN
China
Prior art keywords
image
dimensional code
processing module
result information
image processing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110992843.4A
Other languages
Chinese (zh)
Other versions
CN113436196A (en
Inventor
张锦辉
李少康
张树威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Xiongxing Holding Group Co ltd
Original Assignee
Guangzhou Xiongxing Plastic Products Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangzhou Xiongxing Plastic Products Co ltd filed Critical Guangzhou Xiongxing Plastic Products Co ltd
Priority to CN202110992843.4A priority Critical patent/CN113436196B/en
Publication of CN113436196A publication Critical patent/CN113436196A/en
Application granted granted Critical
Publication of CN113436196B publication Critical patent/CN113436196B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404Methods for optical code recognition
    • G06K7/146Methods for optical code recognition the method including quality enhancement steps
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30108Industrial image inspection
    • G06T2207/30144Printing quality

Abstract

The invention discloses a two-dimensional code film production management system based on an image recognition technology, which comprises an on-line terminal used for controlling a two-dimensional code film production line and also comprises: the image acquisition device is used for acquiring and outputting the image of the sample film printed with the two-dimensional code; the primary image processing module is connected to the image acquisition device and used for performing out-of-focus detection on the image information output by the image acquisition device and transmitting primary result information to the online terminal; and the online terminal is used for introducing an adjusting model based on the membrane sample effect to analyze the result information and outputting corresponding production regulation and control information. This application has the effect of improving two-dimensional code membrane printing definition.

Description

Two-dimensional code film production management system based on image recognition technology
Technical Field
The application relates to the technical field of composite film production and processing, in particular to a two-dimensional code film production management system based on an image recognition technology.
Background
Along with the development of the internet, the popularization of the two-dimensional code is more and more extensive, so that people can more conveniently consume or surf the internet in daily life, and accordingly, the substrate requirements for printing and painting the two-dimensional code are more and more large.
At present, most of the two-dimensional code bottom plates on the market are made of paper, paper plastic, PVC and other plastic film materials. The paper is easy to be affected with damp and damaged by environmental factors such as weather, while the industrial standards and technical parameters of the plastic films are different, so that products with the problems of unclear spray painting, ink blurring and the like are easy to appear, and therefore the application provides a new technical scheme.
Disclosure of Invention
In order to improve the product quality of two-dimensional code, the application provides a two-dimensional code film production management system based on image recognition technology.
The utility model provides a two-dimensional code film production management system based on image recognition technology, includes the on-line terminal that is used for doing control to two-dimensional code film production line, still includes:
the image acquisition device is used for acquiring and outputting the image of the sample film printed with the two-dimensional code; and the number of the first and second groups,
the primary image processing module is connected to the image acquisition device and used for executing out-of-focus detection on the image information output by the image acquisition device and transmitting primary result information to the online terminal;
and the online terminal is used for introducing an adjusting model based on the membrane sample effect to analyze the result information and outputting corresponding production regulation and control information.
Optionally, the primary image processing module performs out-of-focus detection in a manner without a reference image.
Optionally, the system further comprises a secondary image processing module; the secondary image processing module is connected with the primary image processing module and is used for executing Gaussian blur processing on qualified primary result information, comparing the change quantity of adjacent pixel values of the original image and the processed image and transmitting secondary result information to the online terminal;
optionally, the device further comprises a roughness detection module, wherein the roughness detection module is used for detecting the roughness of the printing surface of the sample film and transmitting the roughness to an on-line terminal; the on-line terminal is also used for establishing a relation curve of the roughness and the definition of the two-dimensional code.
Optionally, the system further comprises a fault processing module, wherein the fault processing module is connected to the primary image processing module, the secondary image processing module and the online terminal, and is used for comparing result information corresponding to two adjacent samples and transmitting a self-checking instruction to the secondary image processing module and the online terminal when the result information is consistent.
Optionally, the secondary image processing module is configured to respond to the self-checking instruction, perform gaussian blur processing on image information sampled at a previous time, compare a variation between an original image and a neighboring pixel value of the processed image, compare current result information with original result information, and perform consistency determination; and the on-line terminal is used for responding to the self-checking instruction, outputting self-checking information for controlling equipment of the two-dimensional code production line and obtaining feedback.
Optionally, the system further comprises an integration module, wherein the integration module is connected with the secondary image processing module and the online terminal, and is used for counting the total production amount and the production time of the two-dimensional code film between nodes with unqualified definition and calculating the production efficiency.
In summary, the present application includes at least one of the following beneficial technical effects:
1. performing defocusing detection based on-site sampling, distinguishing the definition of the defocusing detection, judging whether the defocusing detection is qualified or not, and timely regulating and controlling production equipment after the defocusing detection is not qualified; the out-of-focus detection is carried out in a mode without a reference image, accidental interference caused by a single two-dimensional code pattern is avoided, and the detection result is more real and effective;
2. the detection based on the sample is divided into two parts, one time can be simple, such as Brenner algorithm processing, resources are saved, and meanwhile, coarse screening is rapidly completed; secondly, performing secondary detection on the qualified primary image, so that the detection accuracy is improved, and the high-standard production requirement is met;
3. and carrying out roughness detection on the sample, establishing a relation curve between the roughness detection and the definition for the reference of workers, introducing manual intervention, and avoiding the influence on normal production and processing caused by system false response when the detection is interfered by the reflection of the sample film.
Drawings
FIG. 1 is a system architecture diagram of the present application;
fig. 2 is a flowchart of the gaussian blurring process of the present application.
Detailed Description
The present application is described in further detail below with reference to figures 1-2.
The embodiment of the application discloses two-dimensional code film production management system based on image recognition technology, which aims at being matched with a two-dimensional code production line to endow products with more excellent spray painting printing performance.
Referring to fig. 1, the two-dimensional code film production management system based on the image recognition technology includes an on-line terminal and an image acquisition device in the form of hardware, and further includes a software module constructed based on the hardware, including a primary image processing module.
The online terminal refers to a general integrated PC (personal computer) used for controlling equipment feeding, surface roughening treatment and the like on a two-dimensional code production line, and the PC is networked.
The image acquisition device comprises a high-definition camera set which is arranged in a detection room of a factory area or a sample preparation working area. In the production process, equipment for printing the two-dimensional code is arranged at the detection position, so that the two-dimensional code can be printed on the produced two-dimensional code sampling site according to the production requirement; the printed film sample is placed on a platform in a high-definition camera set shooting area to realize image acquisition and output of the sample film; the data output by the image acquisition device can be uploaded to a certain pre-built holder or a server of a factory to wait for analysis and processing.
And the primary image processing module is constructed based on an image recognition technology and is preset in a specified hardware base, such as a cloud platform server. The primary image processing module is used for executing out-of-focus detection on the acquired image information so as to judge the definition of the acquired image information, and specifically comprises the following steps:
considering that the two-dimensional code has various patterns, if the test is only a fixed pattern, it is difficult to ensure whether the printing quality is coincident, so the two-dimensional code on the sample film is set to be random to ensure the detection effect; on the basis, the out-of-focus detection is performed in a reference-map-free manner, and the reference-map-free manner comprises the following steps:
performing Brenner algorithm processing on the grayed image, namely calculating the square of the gray difference of two adjacent pixels by using a Brenner gradient function to obtain a definition result; the Brenner gradient function is as follows:
Figure 100002_DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 973248DEST_PATH_IMAGE002
representing image correspondences
Figure 100002_DEST_PATH_IMAGE003
Corresponding pixel point
Figure 624809DEST_PATH_IMAGE004
Is determined by the gray-scale value of (a),
Figure 100002_DEST_PATH_IMAGE005
and calculating the image definition. The resolution calculation method is relatively simple and is chosen because it is the primary analysis process and does not have to be too accurate.
Primary result information obtained by primary image processing module defocusing detection is fed back to the online terminal, the online terminal is used for introducing an adjustment model based on the membrane sample effect to analyze the result information and outputting corresponding production regulation and control information, namely the system can be used for carrying out real-time regulation and control on control parameters of a production line according to a sample test result sampled in real time, and improving the production process so as to effectively improve the quality of the produced two-dimensional codes.
The rough processing image can quickly distinguish samples with poor definition; for the products qualified in the primary detection, the system also comprises a secondary image processing module, and the module is used for performing higher-precision analysis processing, so that the detection accuracy is improved on one hand, and the production requirements of higher standards are met on the other hand. The secondary image processing module is connected to the primary image processing module and is used for executing Gaussian blur processing on qualified (meeting the first threshold) primary result information and comparing the change quantity of the adjacent pixel values of the original image and the processed image. The gaussian blurring process is used to differentiate the two-dimensional code images with relatively good definition by high-frequency component display, and perform depth evaluation, and the flow is shown in fig. 2. And the secondary result information is also fed back to the online terminal.
Supplementary explanation: in the upper part of fig. 2, the change of the gray level value of the adjacent pixel from the image to be evaluated is the change of the adjacent pixel value of the original image;
in the lower part of fig. 2, the change of the gray level of the adjacent pixels from the blurred image is the change of the adjacent pixel values of the processed image;
the comparison analysis in fig. 2 is to compare the change amounts of the adjacent pixel values of the original image and the processed image.
The introduction of the on-line terminal is based on the analysis of the resulting information by an adjustment model of the film-like effect, such as: when the primary result information does not accord with a preset first threshold value, determining a point A of a plasticizing component in the enlargement production process, wherein A is a set minimum single adjustment amount; if the secondary result information does not meet the preset second threshold value, the original set formula is called, the corresponding control parameters (the offset interference of the equipment is eliminated) are output again according to the formula, and the user is judged to be required to be prompted after two continuous offset adjustments. And the specific setting of model adjustment is realized by manually changing each process parameter by a worker, verifying the detection result, recording the adjustment quantity and the result variable quantity of each parameter in the process to obtain a relation table, and training the adjustment model according to the relation table.
The system further comprises a roughness detection module, wherein the roughness detection module is used for detecting the printing surface roughness of the sample film and transmitting the printing surface roughness to the online terminal. The roughness of the sample film, or the light reflection degree of the film, is detected because certain interference exists in the image acquisition process due to the problem of film light reflection, and the film needs to be removed for the purpose.
The roughness detection module comprises an artificial light source and a spectrum detection mechanism; the roughness of the sample film can be evaluated according to the obtained light intensity change by irradiating the sample film with an artificial light source such as laser and receiving and detecting the reflected light by a spectrum detection mechanism. The detection result of the spectrum detection mechanism is transmitted to the online terminal, the detection result of each time is recorded, a relation curve of the roughness and the definition of the two-dimensional code is established, the relation curve can be referred by a worker, whether the definition detection is interfered by the roughness of the sample film or not is judged, and the automatic adjustment of a manual intervention system is carried out, so that the influence on normal production and processing caused by the wrong regulation and control of the system is avoided.
The system also comprises a fault processing module, and the fault processing module is connected to the primary image processing module, the secondary image processing module and the online terminal. The fault processing module is used for comparing result information corresponding to two adjacent samples, namely comparing primary result information of the sample film of the Nth time with primary result information of the sample film of the (N-1) th time, and comparing secondary result information of the sample film of the Nth time with secondary result information of the sample film of the (N-1) th time; and when the comparison result is twice consistent, transmitting a self-checking instruction to the secondary image processing module and the online terminal.
The reason why the image is not transmitted to the primary image processing module is that the primary image processing is rough processing, the resolution level is not high, normal production can occur, and the secondary image processing is different.
The secondary image processing module is used for responding to the self-checking instruction, executing Gaussian fuzzy processing on the image information sampled at the previous time, comparing the change quantity of adjacent pixel values of the original image and the processed image, comparing the current result information with the original result information, and judging consistency; and the on-line terminal is used for responding to the self-checking instruction, outputting self-checking information for controlling equipment of the two-dimensional code production line and obtaining feedback. After the two are self-checked, the system can evaluate whether the fault appears in the image processing link and the equipment of the production line or eliminate the two; when the two are eliminated, the fault can be considered to appear in the sample two-dimensional code printing link.
According to the content, the fault point can be conveniently found out in time by the working personnel when the abnormity is detected so as to be eliminated.
In the foregoing, it is mentioned that the production line equipment has the problem of control offset during use (caused by aging, excessive temperature, etc.), and for this reason, the system further includes an integration module, which is connected with the secondary image processing module and the on-line terminal. The comprehensive module receives and acquires the operation data of the three modules and records the operation data, and is used for counting the total production amount and the production time of the two-dimensional code film among nodes with unqualified definition (unqualified secondary results), and calculating the production efficiency. According to the information, the maintenance node of the production line equipment can be conveniently confirmed by the staff, the production plan is improved, the equipment is reasonably utilized, and the product quality is improved.
The above embodiments are preferred embodiments of the present application, and the protection scope of the present application is not limited by the above embodiments, so: all equivalent changes made according to the structure, shape and principle of the present application shall be covered by the protection scope of the present application.

Claims (4)

1. The utility model provides a two-dimensional code film production management system based on image recognition technology, is including being used for doing the terminal on the line of control to two-dimensional code film production line, its characterized in that still includes:
the image acquisition device is used for acquiring and outputting the image of the sample film printed with the two-dimensional code; and the number of the first and second groups,
the primary image processing module is connected to the image acquisition device and used for executing out-of-focus detection on the image information output by the image acquisition device and transmitting primary result information to the online terminal;
the online terminal is used for introducing an adjusting model based on the membrane sample effect to analyze result information and outputting corresponding production regulation and control information;
the mode without reference picture includes:
performing Brenner algorithm processing on the grayed image, namely calculating the square of the gray difference of two adjacent pixels by using a Brenner gradient function to obtain a definition result; the Brenner gradient function is as follows:
Figure DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE002
representing image correspondences
Figure DEST_PATH_IMAGE003
Corresponding pixel point
Figure DEST_PATH_IMAGE004
Is determined by the gray-scale value of (a),
Figure DEST_PATH_IMAGE005
calculating the result of the image definition;
the primary image processing module performs out-of-focus detection in a reference-image-free manner;
the system also comprises a secondary image processing module; the secondary image processing module is connected with the primary image processing module and is used for executing Gaussian blur processing on qualified primary result information, comparing the change quantity of adjacent pixel values of the original image and the processed image and transmitting secondary result information to the online terminal;
the roughness detection module comprises an artificial light source and a spectrum detection mechanism, and is used for detecting the printing surface roughness of the sample film and transmitting the roughness to the on-line terminal; the online terminal is further used for establishing a relation curve of the roughness and the definition of the two-dimensional code and judging whether the definition detection is interfered by the roughness of the sample film.
2. The two-dimensional code film production management system based on the image recognition technology as claimed in claim 1, wherein: the system further comprises a fault processing module, wherein the fault processing module is connected to the primary image processing module, the secondary image processing module and the online terminal, and is used for comparing result information corresponding to two adjacent samples and transmitting a self-checking instruction to the secondary image processing module and the online terminal when the result information is consistent.
3. The two-dimensional code film production management system based on the image recognition technology as claimed in claim 2, wherein: the secondary image processing module is used for responding to the self-checking instruction, executing Gaussian fuzzy processing on the image information sampled at the previous time, comparing the change quantity of adjacent pixel values of the original image and the processed image, comparing the current result information with the original result information, and judging consistency; and the on-line terminal is used for responding to the self-checking instruction, outputting self-checking information for controlling equipment of the two-dimensional code production line and obtaining feedback.
4. The two-dimensional code film production management system based on the image recognition technology as claimed in claim 1, wherein: the system further comprises an integrated module, wherein the integrated module is connected with the secondary image processing module and the online terminal and used for counting the total production amount and the production time of the two-dimensional code film between the nodes with unqualified definition and calculating the production efficiency.
CN202110992843.4A 2021-08-27 2021-08-27 Two-dimensional code film production management system based on image recognition technology Active CN113436196B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110992843.4A CN113436196B (en) 2021-08-27 2021-08-27 Two-dimensional code film production management system based on image recognition technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110992843.4A CN113436196B (en) 2021-08-27 2021-08-27 Two-dimensional code film production management system based on image recognition technology

Publications (2)

Publication Number Publication Date
CN113436196A CN113436196A (en) 2021-09-24
CN113436196B true CN113436196B (en) 2021-12-10

Family

ID=77798208

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110992843.4A Active CN113436196B (en) 2021-08-27 2021-08-27 Two-dimensional code film production management system based on image recognition technology

Country Status (1)

Country Link
CN (1) CN113436196B (en)

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1309565C (en) * 2004-09-02 2007-04-11 中国印钞造币总公司 On-line automatic controlsystem for printing quality
US8050502B2 (en) * 2006-06-21 2011-11-01 Namco Bandai Games Inc. Two-Dimensional code generation method, two-dimensional code, two-dimensional code recognition method, and image recognition device
DE102014210690A1 (en) * 2014-06-05 2015-12-17 Heidelberger Druckmaschinen Ag Method for identifying print control elements for quality data acquisition
CN108109147B (en) * 2018-02-10 2022-02-18 北京航空航天大学 No-reference quality evaluation method for blurred image
WO2019208048A1 (en) * 2018-04-27 2019-10-31 京セラドキュメントソリューションズ株式会社 Ink discharge device, printing device, and method for controlling ink discharge device
CN110889304B (en) * 2018-09-11 2023-04-28 杭州海康威视数字技术股份有限公司 Two-dimensional code quality evaluation method and device, storage medium, electronic equipment and system
CN109795226A (en) * 2019-01-25 2019-05-24 浙江爱迪尔包装股份有限公司 A kind of technique with cold wave spray printing variable two-dimension code
US10942687B2 (en) * 2019-06-28 2021-03-09 Ncr Corporation Print quality monitoring and correction
CN211741094U (en) * 2019-10-31 2020-10-23 深圳市凯瑞奇自动化技术有限公司 Surface defect detection device for transparent mirror printing and gold stamping process

Also Published As

Publication number Publication date
CN113436196A (en) 2021-09-24

Similar Documents

Publication Publication Date Title
CN104992449B (en) Information identification and surface defect online test method based on machine vision
CN110389127B (en) System and method for identifying metal ceramic parts and detecting surface defects
CN107437094B (en) Wood board sorting method and system based on machine learning
CN107229930B (en) Intelligent identification method for numerical value of pointer instrument
CN109584227A (en) A kind of quality of welding spot detection method and its realization system based on deep learning algorithm of target detection
CN110853015A (en) Aluminum profile defect detection method based on improved Faster-RCNN
CN106546263B (en) A kind of laser leveler shoot laser line detecting method based on machine vision
CN106556611A (en) Chromatograp defect automatic checkout system and detection method based on machine vision
CN110610199B (en) Automatic optical detection method for printed circuit board resistance element welding spot based on svm and xgboost
CN110096980A (en) Character machining identifying system
CN102456142A (en) Analysis method for smoke blackness based on computer vision
CN113483682B (en) Gap measurement method and system based on machine vision
CN109444172A (en) A kind of automatic optical detection device and its method suitable for artificial intelligence detection PCB
CN114066848B (en) FPCA appearance defect visual detection system
CN115908432B (en) Material output quality detection system and prediction method
CN114638797A (en) Method and device for detecting copper surface defects based on linear array camera
CN108764278A (en) A kind of the self study industrial intelligent detecting system and method for view-based access control model
CN113822882A (en) Circuit board surface defect detection method and device based on deep learning
CN110567967B (en) Display panel detection method, system, terminal device and computer readable medium
CN113436196B (en) Two-dimensional code film production management system based on image recognition technology
CN102680488B (en) Device and method for identifying massive agricultural product on line on basis of PCA (Principal Component Analysis)
CN116740449A (en) Shaving form detection method and system based on AI (advanced technology attachment) computer vision technology
CN115482227A (en) Machine vision self-adaptive imaging environment adjusting method
CN209215256U (en) A kind of automatic optical detection device suitable for artificial intelligence detection PCB
CN115479891A (en) Automatic detection system and method for circuit board mounted components based on image recognition

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: Room 101, No. 133 Baisha Commercial Street, Baiyun District, Guangzhou City, Guangdong Province, 510000

Patentee after: Guangdong Xiongxing Holding Group Co.,Ltd.

Address before: 510000 group 12, Baisha village, Guangcong Road, Liangtian Town, Baiyun District, Guangzhou City, Guangdong Province

Patentee before: GUANGZHOU XIONGXING PLASTIC PRODUCTS CO.,LTD.

CP03 Change of name, title or address