CN113870212B - Visual identification defect detection method based on printed matter characters - Google Patents
Visual identification defect detection method based on printed matter characters Download PDFInfo
- Publication number
- CN113870212B CN113870212B CN202111119007.1A CN202111119007A CN113870212B CN 113870212 B CN113870212 B CN 113870212B CN 202111119007 A CN202111119007 A CN 202111119007A CN 113870212 B CN113870212 B CN 113870212B
- Authority
- CN
- China
- Prior art keywords
- image
- data
- detected
- processing method
- result
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 230000000007 visual effect Effects 0.000 title claims abstract description 26
- 230000007547 defect Effects 0.000 title claims abstract description 25
- 238000007781 pre-processing Methods 0.000 claims abstract description 52
- 238000007639 printing Methods 0.000 claims abstract description 28
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 238000003672 processing method Methods 0.000 claims description 112
- 238000000034 method Methods 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 7
- 230000006872 improvement Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a visual identification defect detection method based on printed matter characters, which realizes fine printing defect detection, improves the accuracy of printed matter character detection, is provided with a network module for data interaction among an image matching module, a visual data acquisition device and an OCV detection module, uploads detection data to a database module for storage and update, and acquires to-be-detected data of a character printed matter to be detected by using the visual data acquisition device; dividing the data to be detected according to the region to obtain an image to be detected, and marking; and preprocessing the marked image to be detected.
Description
Technical Field
The invention relates to the technical field of visual identification defect detection, in particular to a visual identification defect detection method based on printed matter characters.
Background
In the printing process of the printed product, a large amount of automatic printing causes printing defects of characters, so that the qualification rate of the printed product is reduced, and the production efficiency is affected. With the development of modern printing industry, the requirements of people on printing technology are higher and higher, so that the printed matter must be strictly detected before leaving the factory, and the reject ratio is controlled.
In the prior art, the manual visual inspection is replaced by the machine vision, so that the manpower resources are saved, and the detection rate is improved. However, in actual work, the process requirements of different areas and different characters of a piece of printed matter are different, different areas and different characters need to be distinguished, and different pretreatment schemes and different detection modes are adopted for detection, so that the technical problem of weak applicability exists.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the purposes of the invention is to provide a visual identification defect detection method based on printed matter characters, so that fine printing defect detection is realized, and the accuracy of printed matter character detection is improved.
One of the purposes of the invention is realized by adopting the following technical mode:
a visual identification defect detection method based on printed matter characters comprises the following steps:
step 1: acquiring the data to be detected of the character printed matter to be detected by using a visual data acquisition device;
step 2: dividing the data to be detected according to the region to obtain an image to be detected, and marking;
step 3: preprocessing the marked image to be detected;
step 4: OCV detection is carried out on the preprocessed image to be detected, so that the printing quality score of the image to be detected is obtained, if the printing quality score of the image to be detected is lower than a preset score, the image to be detected is a defective printed matter, and the detection is ended; if the print quality score of the image to be detected is higher than the preset score, the image to be detected is a qualified product;
step 5: and weighting the image quality scores of all the areas, calculating the sum of the quality scores, and judging whether the character printed matter to be tested has defects according to the printing process standard.
Further, the preprocessing method of the image to be detected in the step 3 is as follows:
s100: obtaining first image data to be detected and a first processing method according to the image matching module;
s200: obtaining character printing data and preprocessing data of the image to be detected according to the first image data to be detected, and obtaining a first image area building result to be detected according to the character printing data and the preprocessing data of the image to be detected;
s300: obtaining an occupation weight value of the image to be detected according to the image to be detected occupation set of the image to be detected occupation data of the created area;
s400: selecting the position coordinates of a first area according to the occupation weight value of the image to be detected and the preprocessing data to obtain a first selection result;
and obtaining a first region building result according to the first selection result.
Further, step S400 further includes:
s410: obtaining a first processing method adjacent range set, wherein the first processing method adjacent range set is a set of three images in a processing process range sequence with the smallest difference with the first processing method in the preprocessing data;
s420: the first area is arranged in an adjacent mode according to the first processing method adjacent range set, and a first arrangement result is obtained;
s430: judging the ink transfer rate of the image to be detected according to the first arrangement result to obtain a first judgment result; and adjusting the first arrangement result according to the first judgment result and the occupation weight value of the image to be detected to obtain the first selection result.
Further, the method includes step S500, and step S500 includes:
s510: an adjustment processing step of obtaining the created area under the first selection result, and obtaining a first adjustment parameter according to the adjustment processing step;
s520: a first preprocessing step of inputting first input data of a printed matter and obtaining the first target according to the first input data; performing mode reliability judgment on the first selection result according to the first preprocessing step and the first adjusting parameter to obtain a second judgment result;
s530: adjusting the first selection result according to the second judgment result to obtain a second selection result;
s540: and obtaining the first region building result according to the second selection result.
Further, including step S500 further includes:
s550: obtaining adjacent area preprocessing data according to the adjacent image area data;
s560: obtaining a processing method difference set according to the adjacent area preprocessing data and the first processing method;
s570: judging whether the processing method difference sets all meet a first preset difference set or not;
s580: when the image processing method which does not meet the first preset difference set exists in the processing method difference set, obtaining a region corresponding to the processing method difference;
s590: and carrying out a modification pretreatment step on the region and the first region to obtain the second region construction result.
Further, step S520:
s521: obtaining first interference parameter data of the region to the second region construction result according to the processing method difference;
s522: adjusting the processing method control data of the second region building result according to the first interference parameter data to obtain a first processing method control value;
s523: and performing image preprocessing setting management on the first target according to the first processing method control value and the second region construction result.
Further, step S521 further includes:
s5211: when the processing method difference set meets the first preset difference set, second interference parameter data of the processing method difference set on the second region construction result is obtained;
s5212: adjusting the processing method control data of the second region building result according to the second interference parameter data to obtain a second processing method control parameter;
s5213: and performing image preprocessing setting management on the first target according to the second processing method control parameters and the second region building result.
Furthermore, a network module is arranged for data interaction among the image matching module, the visual data acquisition device and the OCV detection module, and the detection data is uploaded to a database module for storage and updating.
Compared with the prior art, the invention has the advantages that:
the pretreatment schemes of printed matters such as different ink transfer rates, different materials, different printing processes, different characters, images and the like are treated differently by controlling the personalized and refined pretreatment methods of different areas and characters, so that the accuracy of OCV detection is improved.
The foregoing description is only an overview of the technical aspects of the present invention, and may be implemented according to the content of the specification in order to make the technical means of the present invention more clearly understood, and in order to make the above and other objects, features and advantages of the present invention more clearly understood, the following detailed description of the preferred embodiments will be given with reference to the accompanying drawings.
Drawings
FIG. 1 is a schematic diagram showing steps of a visual recognition defect detection method in the present embodiment;
fig. 2 is a block diagram of software and hardware equipment of the visual recognition defect detection method in the present embodiment.
Description of the embodiments
The present invention will be further described with reference to the accompanying drawings and detailed description, which should be construed as being capable of forming new embodiments by any combination of the embodiments or technical features described below without conflict. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 2, a visual recognition defect detection method based on printed matter characters is provided with a network module for data interaction among an image matching module, a visual data acquisition device and an OCV detection module, and uploads detection data to a database module for storage and update.
The network module can select 5G, NB-IOT communication protocol, the visual data acquisition device is a camera sensor and related light supplementing and reflecting equipment, the image matching module and the OCV detection module are calculator application programs, and the calculator is used for implementation and operation.
Referring to fig. 1, the method specifically comprises the following steps:
step 1: acquiring the data to be detected of the character printed matter to be detected by using a visual data acquisition device;
step 2: dividing the data to be detected according to the region to obtain an image to be detected, and marking;
step 3: preprocessing the marked image to be detected;
the processing method includes but is not limited to graying, binarization, noise reduction, inclination correction, text segmentation and the like, in the processing process, each method can be repeatedly used in a single method according to the specific image condition to be detected, or each method is overlapped, used for multiple times and the like, the conventional scheme is that each method is sequentially processed, the specific flow can be increased or decreased according to different image data to be detected and printing effects, and the defect detection requirement is met, so that the embodiment is not repeated;
step 4: OCV detection is carried out on the preprocessed image to be detected, so that the printing quality score of the image to be detected is obtained, if the printing quality score of the image to be detected is lower than a preset low score, the image to be detected is a defective printed matter, and the detection is ended; if the print quality score of the image to be detected is higher than Gao Fenzhi, the image to be detected is a qualified product;
step 5: and weighting the image quality scores of all the areas, calculating the sum of the quality scores, and judging whether the character printed matter to be tested has defects according to the printing process standard.
The preprocessing method of the image to be detected in the step 3 is as follows:
s100: obtaining first image data to be tested and a first processing method according to an image matching module;
s200: obtaining character printing data and preprocessing data of the image to be detected according to the first image data to be detected, and obtaining a first image area building result to be detected according to the character printing data and the preprocessing data of the image to be detected;
s300: obtaining an occupation weight value of the image to be detected according to the occupation set of the image to be detected of the occupation data of the image to be detected of the created area;
s400: selecting position coordinates of a first area according to the occupation weight value of the image to be detected and the preprocessing data to obtain a first selection result;
and obtaining a first region building result according to the first selection result.
Specifically, the image matching module refers to a matching program for carrying out image and character recognition; the first to-be-tested image data refers to image data which is printed, preferably a printed product matched with the image matching module, and a printed image is provided for each area in the printed product area according to the first to-be-tested image; calling all the areas and the preprocessing data corresponding to the areas in a one-to-one correspondence mode and inputting the areas and the preprocessing data into a first printing image; the occupation weight value of the image to be detected refers to the occupation weight determined according to the size of the image to be detected occupied by all areas in the printing area, and the occupation weight value of the image to be detected and the preprocessing data are marked for all areas; the first selection result refers to selecting a proper processing method according to the respective image occupation weight values to be detected and the preprocessing data of all the processed characters, and the determination mode is an example without limitation:
embodiments are described below: taking a first target as an example, firstly, determining a reasonable processing method in a printing area which is close to a first processing method of the first target according to the occupation weight value of an image to be detected, and then completing the construction of the first area;
and determining a proper processing method according to the occupation weight values of all the images to be detected of the stored characters and the preprocessing data, and adjusting the preprocessing mode aiming at the occupation rate of the images to be detected containing different characters, thereby improving the pertinence.
Step S400 further includes:
s410: obtaining a first processing method adjacent range set, wherein the first processing method adjacent range set is a set of three images in a processing process range sequence with the smallest difference with the first processing method in the preprocessing data;
s420: according to the first processing method adjacent range set, carrying out adjacent arrangement on the first area to obtain a first arrangement result;
s430: judging the ink transfer rate of the image to be detected according to the first arrangement result to obtain a first judgment result; and adjusting the first arrangement result according to the first judgment result and the occupation weight value of the image to be detected to obtain a first selection result.
Specifically, the first processing method proximity range set refers to region data corresponding to four processing methods that are the smallest in difference from the first processing method. The preferred determination method is as follows: sequencing the areas according to the processing methods, so that the image areas of four adjacent processing methods of each processing method in the preset processing method can be obtained; the first arrangement result refers to that the first processing method and the four adjacent processing areas are approximately processed according to the first processing method adjacent range set, the four adjacent processing methods of the four adjacent processing methods are respectively read to be arranged in an adjacent mode, and when all the areas are distributed, the arrangement result is obtained; the first judgment result refers to judging by using ink transfer for the image to be detected caused by the arrangement mode only taking the gradient of the processing method into consideration in the first arrangement result, and a preset value of ink transfer for the image to be detected is preferably set: extracting arrangement positions which do not accord with the preset ink transfer value of the image to be detected in the first arrangement result, adjusting the arrangement positions according to the occupation weight value of the image to be detected to obtain an analysis arrangement mode with abnormal ink transfer rate of the image to be detected, and taking the final processing arrangement mode as a first selection result to obtain the analysis arrangement mode with higher pertinence.
Comprising step S500, step S500 comprising:
s510: an adjustment processing step of obtaining the created area under the first selection result, and obtaining a first adjustment parameter according to the adjustment processing step;
s520: a first preprocessing step of inputting first input data of a printed matter and obtaining a first target according to the first input data; performing mode reliability judgment on the first selection result according to the first pretreatment step and the first adjustment parameter to obtain a second judgment result;
s530: adjusting the first selection result according to the second judgment result to obtain a second selection result;
s540: and obtaining a first region building result according to the second selection result.
Specifically, the first adjustment parameter refers to a parameter for adjusting the arrangement position of each area after being determined according to the first selection result; the first preprocessing step refers to first target preprocessing step data read from first input data; the second judgment result refers to whether the comparison is reasonable or not according to the arrangement position of the area corresponding to the first adjustment parameter and the first preprocessing step, including but not limited to: different characters and different image preprocessing steps are unreasonable if simple characters need to be processed preferentially than complex characters. The second selection result refers to that the image which does not accord with the first pretreatment step in the first selection result is extracted, and the arrangement mode of the areas which accord with the first pretreatment step is adjusted to obtain a result on the basis of the first selection result; and adjusting all the areas according to the second selection result.
The arrangement result of the region conforming to the pretreatment step is obtained by adjusting the first selection result according to the first pretreatment step of the first object, and the matching efficiency of the image to be detected is improved.
Step S500 further includes:
s550: obtaining adjacent area preprocessing data according to the adjacent image area data;
s560: obtaining a processing method difference set according to the adjacent area preprocessing data and the first processing method;
s570: judging whether the processing method difference sets all meet a first preset difference set or not;
s580: when an image processing method which does not meet the first preset difference set exists in the processing method difference set, obtaining a region corresponding to the processing method difference;
s590: and carrying out a modification pretreatment step on the region and the first region to obtain a second region construction result.
Specifically, the vicinity area pre-processing data refers to pre-processing data corresponding to a vicinity area; the processing method difference set refers to a difference data set for calculating the adjacent area pretreatment data and the first processing method data of the first area; the first preset difference refers to the maximum difference that may affect the printing effect of each other when the difference of the pre-processed data of the first area and the neighboring area is too large; traversing and comparing the difference data set with the first preset difference one by one to obtain an adjacent area corresponding to the difference data which does not meet the requirement, and carrying out a modification pretreatment step on the adjacent area and the first area to achieve the aim that the processed image is suitable for detection and complete the construction of the second area.
By judging the difference of the processing methods between the first area and the adjacent areas, the mode of changing the preprocessing steps between the characters which do not accord with the first preset difference is adopted, so that the preprocessing effect is improved, and the technical effect of improving the image and character detection accuracy is achieved.
Step S520:
s521: obtaining first interference parameter data of a region-to-second region construction result according to the processing method difference;
s522: adjusting the processing method control data of the second region construction result according to the first interference parameter data to obtain a first processing method control value;
s523: and performing image preprocessing setting management on the first target according to the control value of the first processing method and the second region construction result.
Specifically, the first interference parameter data refers to obtaining parameter data according to the degree of influence of the processing method difference of the first region and the neighboring region on the processing method of the first region when the processing method difference set does not meet the first preset difference set; the first processing method control value refers to processing method control data for adjusting a second region construction result originally set according to the first processing method according to the first interference parameter data, and the adjustment manner includes but is not limited to: dividing the influence effect into two types of improvement and reduction according to the general logic, when the first interference parameter data is judged to be classified as improvement, indicating that the corresponding adjacent area processing method is higher in effect, and improving the actual processing method of the first area, so that a set processing method strategy for correspondingly reducing the first area is obtained, accurate pretreatment data of the first area is monitored in real time, an accurate regulation value is determined, and regulation is completed; when the first interference parameter data is judged to be classified as lowering, the fact that the corresponding adjacent area processing method is lower is indicated, and the actual processing method of the first area is lowered, so that a strategy of the set processing method which needs to be correspondingly improved, of the first area is obtained, accurate preprocessing data of the first area is monitored in real time, an accurate adjusting value is determined, and adjustment is completed.
The processing method is set by adjusting the influence degree of the difference of the processing methods of the first area and the adjacent area on the processing method of the first area, so that the control of the fine processing method is realized, and the accuracy and individuation degree of image and character detection are improved.
Step S521 further includes:
s5211: when the processing method difference set meets the first preset difference set, second interference parameter data of the processing method difference set on a second region construction result are obtained;
s5212: adjusting the processing method control data of the second region construction result according to the second interference parameter data to obtain second processing method control parameters;
s5213: and performing image preprocessing setting management on the first target according to the second processing method control parameters and the second region construction result.
Specifically, the second interference parameter data refers to obtaining parameter data according to the degree of influence of the processing method difference of the first region and the neighboring region thereof on the processing method of the first region when the processing method difference set meets the first preset difference set; the second processing method control parameter refers to processing method control data for adjusting a second region construction result originally set according to the first processing method according to second interference parameter data, and the adjustment manner includes but is not limited to: dividing the influence effect into two types of improvement and reduction according to the general logic, when judging that the second interference parameter data is classified as improvement, indicating that the corresponding adjacent area processing method is higher, and improving the actual processing method of the first area, thereby obtaining a set processing method strategy for correspondingly reducing the first area, monitoring the accurate pretreatment data of the first area in real time, determining an accurate regulation value, and finishing regulation; when the second interference parameter data is judged to be classified as lowering, the fact that the corresponding adjacent area processing method is lower is indicated, and the actual processing method of the first area is lowered, so that a setting processing method strategy for correspondingly raising the first area is obtained, accurate preprocessing data of the first area is monitored in real time, an accurate adjusting value is determined, and adjustment is completed.
The processing method is set by adjusting the influence degree of the difference of the processing methods of the first area and the adjacent area on the processing method of the first area, so that the control of the fine processing method is realized, and the accuracy and individuation degree of image and character detection are improved.
The above embodiments are only preferred embodiments of the present invention, and should not be construed as limiting the scope of the present invention, and any insubstantial changes and substitutions made by those skilled in the art on the basis of the present invention are intended to be within the scope of the present invention as claimed.
Claims (7)
1. The visual identification defect detection method based on the printed matter characters is characterized by comprising the following steps of:
step 1: acquiring the data to be detected of the character printed matter to be detected by using a visual data acquisition device;
step 2: dividing the data to be detected according to the region to obtain an image to be detected, and marking;
step 3: preprocessing the marked image to be detected;
step 4: OCV detection is carried out on the preprocessed image to be detected, so that the printing quality score of the image to be detected is obtained, and if the printing quality score of the image to be detected is lower than a preset score, the image to be detected is a defective printed matter; if the print quality score of the image to be detected is higher than the preset score, the image to be detected is a qualified product;
step 5: weighting the image quality scores of all the areas, calculating the total sum of the quality scores, and judging whether the character printed matter to be tested has defects according to the printing process standard;
the preprocessing method of the image to be detected in the step 3 is as follows:
s100: obtaining first image data to be tested and a first processing method according to an image matching module;
s200: obtaining character printing data and preprocessing data of the image to be detected according to the first image data to be detected, and obtaining a first image area building result to be detected according to the character printing data and the preprocessing data of the image to be detected;
s300: obtaining an occupation weight value of the image to be detected according to the image to be detected occupation set of the image to be detected occupation data of the created area;
s400: selecting the position coordinates of a first area according to the occupation weight value of the image to be detected and the preprocessing data to obtain a first selection result;
and obtaining a first region building result according to the first selection result.
2. A visual recognition defect detection method based on printed matter characters as claimed in claim 1, characterized in that:
the step S400 specifically includes:
s410: obtaining a first processing method adjacent range set, wherein the first processing method adjacent range set is a set of three images in a processing process range sequence with the smallest difference with the first processing method in the preprocessing data;
s420: the first area is arranged in an adjacent mode according to the first processing method adjacent range set, and a first arrangement result is obtained;
s430: judging the ink transfer rate of the image to be detected according to the first arrangement result to obtain a first judgment result; and adjusting the first arrangement result according to the first judgment result and the occupation weight value of the image to be detected to obtain the first selection result.
3. A visual recognition defect detection method based on printed matter characters as claimed in claim 2, characterized in that:
after step S400, step S500 is further included, where step S500 specifically includes:
s510: an adjustment processing step of obtaining the created area under the first selection result, and obtaining a first adjustment parameter according to the adjustment processing step;
s520: a first preprocessing step of inputting first input data of a printed matter and obtaining a first target according to the first input data; performing mode reliability judgment on the first selection result according to the first preprocessing step and the first adjusting parameter to obtain a second judgment result;
s530: adjusting the first selection result according to the second judgment result to obtain a second selection result;
s540: and obtaining the first region building result according to the second selection result.
4. A visual recognition defect detecting method based on printed matter characters as claimed in claim 3, wherein:
step S500 further includes:
s550: obtaining adjacent area preprocessing data according to the adjacent image area data;
s560: obtaining a processing method difference set according to the adjacent area preprocessing data and the first processing method;
s570: judging whether the processing method difference sets all meet a first preset difference set or not;
s580: when the image processing method which does not meet the first preset difference set exists in the processing method difference set, obtaining a region corresponding to the processing method difference;
s590: and carrying out a modification pretreatment step on the region and the first region to obtain a second region construction result.
5. A method for detecting visual recognition defects based on printed matter characters as defined in claim 4, wherein:
the step S520 specifically includes:
s521: obtaining first interference parameter data of the region to the second region construction result according to the processing method difference;
s522: adjusting the processing method control data of the second region building result according to the first interference parameter data to obtain a first processing method control value;
s523: and performing image preprocessing setting management on the first target according to the control value of the first processing method and the second region construction result.
6. A method for detecting visual recognition defects based on printed matter characters according to claim 5, wherein:
the step S521 specifically includes:
s5211: when the processing method difference set meets the first preset difference set, second interference parameter data of the processing method difference set on the second region construction result is obtained;
s5212: adjusting the processing method control data of the second region building result according to the second interference parameter data to obtain a second processing method control parameter;
s5213: and performing image preprocessing setting management on the first object according to the second processing method control parameters and the second region building result.
7. A method for detecting defects in visual recognition based on printed matter characters as defined in any one of claims 1 to 6, wherein: the system is provided with a network module for data interaction among the image matching module, the visual data acquisition device and the OCV detection module, and uploads detection data to the database module for storage and updating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119007.1A CN113870212B (en) | 2021-09-24 | 2021-09-24 | Visual identification defect detection method based on printed matter characters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111119007.1A CN113870212B (en) | 2021-09-24 | 2021-09-24 | Visual identification defect detection method based on printed matter characters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113870212A CN113870212A (en) | 2021-12-31 |
| CN113870212B true CN113870212B (en) | 2024-01-05 |
Family
ID=78993760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111119007.1A Active CN113870212B (en) | 2021-09-24 | 2021-09-24 | Visual identification defect detection method based on printed matter characters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870212B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109085176A (en) * | 2018-08-20 | 2018-12-25 | 深圳科瑞技术股份有限公司 | A kind of label print quality inspection and data verification method |
| CN109308700A (en) * | 2017-07-27 | 2019-02-05 | 南京敏光视觉智能科技有限公司 | A kind of visual identity defect inspection method based on printed matter character |
| CN109886954A (en) * | 2019-02-28 | 2019-06-14 | 湖南大学 | A kind of printed matter defect inspection method |
| CN110940670A (en) * | 2019-11-25 | 2020-03-31 | 佛山缔乐视觉科技有限公司 | Flexible printing label printing head draft detection system based on machine vision and implementation method thereof |
| CN113034488A (en) * | 2021-04-13 | 2021-06-25 | 荣旗工业科技(苏州)股份有限公司 | Visual detection method of ink-jet printed matter |
-
2021
- 2021-09-24 CN CN202111119007.1A patent/CN113870212B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109308700A (en) * | 2017-07-27 | 2019-02-05 | 南京敏光视觉智能科技有限公司 | A kind of visual identity defect inspection method based on printed matter character |
| CN109085176A (en) * | 2018-08-20 | 2018-12-25 | 深圳科瑞技术股份有限公司 | A kind of label print quality inspection and data verification method |
| CN109886954A (en) * | 2019-02-28 | 2019-06-14 | 湖南大学 | A kind of printed matter defect inspection method |
| CN110940670A (en) * | 2019-11-25 | 2020-03-31 | 佛山缔乐视觉科技有限公司 | Flexible printing label printing head draft detection system based on machine vision and implementation method thereof |
| CN113034488A (en) * | 2021-04-13 | 2021-06-25 | 荣旗工业科技(苏州)股份有限公司 | Visual detection method of ink-jet printed matter |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113870212A (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110672617B (en) | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision | |
| CN113538429B (en) | Mechanical part surface defect detection method based on image processing | |
| CN111833324A (en) | Optical fiber ferrule defect detection method based on deep learning | |
| CN110274908B (en) | Defect inspection apparatus, defect inspection method, and computer-readable recording medium | |
| CN110070008B (en) | Bridge disease identification method adopting unmanned aerial vehicle image | |
| WO2020137222A1 (en) | Defect inspecting device, defect inspecting method, and program for same | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN115082683A (en) | Injection molding defect detection method based on image processing | |
| CN113724231B (en) | Industrial defect detection method based on semantic segmentation and target detection fusion model | |
| CN113109348B (en) | Paddle image transfer printing defect identification method based on machine vision | |
| CN110335262A (en) | A kind of printed matter automatic defect classification method in machine vision | |
| CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
| CN109598681B (en) | No-reference quality evaluation method for image after repairing of symmetrical Thangka | |
| CN111626249B (en) | Method and device for identifying geometric figure in topic image and computer storage medium | |
| CN110909657A (en) | Method for identifying apparent tunnel disease image | |
| CN111275700A (en) | Terminal defect detection method and system based on deep learning | |
| CN112464925A (en) | Mobile terminal account opening data bank information automatic extraction method based on machine learning | |
| CN107590511A (en) | A kind of defect identification method and identifying system the defects of for automatic check machine | |
| CN114612471B (en) | Method for detecting surface defects of complex-texture ceramic tiles | |
| CN113870212B (en) | Visual identification defect detection method based on printed matter characters | |
| CN115170882A (en) | Optimization method of rail wagon part detection network and guardrail breaking fault identification method | |
| CN112837287B (en) | Method and device for extracting defect area of board surface | |
| CN114187286A (en) | Wood plate surface machining quality control method based on machine vision | |
| CN109271977A (en) | The automatic classification based training method, apparatus of bill and automatic classification method, device | |
| CN114820597B (en) | Smelting product defect detection method, device and system based on artificial intelligence |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231212 Address after: 430000 Commercial Building 2, 4th Floor, Jiabaihui Decoration Hardware and Coating City, No. 1 Dongxihu Avenue, Dongxihu District, Wuhan City, Hubei Province (No. 4 and 5, Zone 10) Applicant after: Wuhan Jingyan Technology Co.,Ltd. Address before: 430000 Dongfeng Village, Qiaokou District, Wuhan City, Hubei Province (b-1-2, Changfeng 1st Road) Applicant before: Wuhan Haichuan Color Printing Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |