CN109308700A - A kind of visual identity defect inspection method based on printed matter character - Google Patents
A kind of visual identity defect inspection method based on printed matter character Download PDFInfo
- Publication number
- CN109308700A CN109308700A CN201710621394.6A CN201710621394A CN109308700A CN 109308700 A CN109308700 A CN 109308700A CN 201710621394 A CN201710621394 A CN 201710621394A CN 109308700 A CN109308700 A CN 109308700A
- Authority
- CN
- China
- Prior art keywords
- character
- image
- product
- measured
- printed matter
- 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.)
- Pending
Links
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of visual identity and defect detecting techniques, specially a kind of visual identity defect inspection method based on printed matter character, this method is registrated using shape, defects detection is carried out using OCV, difference shadow method, Detection accuracy is high, suitable for general machine vision platform, include the following steps: step 1: utilizing the image of high speed high-definition camera acquisition standardized product and the image of product to be measured, obtain corresponding ROI region, divide ROI region image character again, obtains the area image of each character；Step 2: shape matching is carried out to the image of product to be measured, ranks coordinate, matching score and the corresponding templates number of the character searched, if matching number is not equal to character number, it is then rejected product, otherwise successively the character of search is detected using OCV detection system, obtains the printing quality score of character.
Description
Technical field
The present invention relates to a kind of visual identity and defect detecting technique, specially a kind of vision based on printed matter character is known
Other defect inspection method.
Background technique
In our life, product related with print character can be seen everywhere.Such as on Key works Drug packing
Date, batch number character, the character in food packaging, the character etc. on consumer package.Due to largely automating print
Brush causes character printing defects occur, and then reduces the qualification rate of product, influences production efficiency.And with modern age printing industry
Development, requirement of the people to printing technology are higher and higher, it is therefore necessary to carry out stringent detection to product before factory, control is not
Qualification rate.
Traditional detection method is detected mainly by human eye, rejects rejected product.The advantage of Manual Visual Inspection is detection mode
Flexibly, a variety of different defects can be determined.However since product variety is more, quantity is big, and manpower consumption's amount is big, and
Prolonged Manual Visual Inspection, human eye are easy fatigue so as to cause judging by accident and failing to judge.And Manual Visual Inspection speed is slow, low efficiency, very
Mostly tiny flaw is not easy to be found, and causes omission factor high, not can guarantee unified quality standard.It is therefore proposed that with machine
Vision replaces Manual Visual Inspection, can not only largely save human resources in this way, additionally it is possible to greatly improve recall rate.
Character defect is mainly that character printing is unintelligible, and character is bitten, and character relative position is unqualified etc., because of above situation
Cause rejection rate is excessively high can seriously affect the quality of production, for strict control disqualification rate, needs when printing to printing
Face character is detected, and each rejected product is rejected in process of production as far as possible.Constantly meet press to high-quality
Amount, high efficiency, inexpensive direction are developed.
To detect printing face character defect, may compare the gray value of the image of standard picture and product to be measured, with to
The image for surveying product subtracts standard picture, is labeled as defect if the difference of corresponding pixel points is greater than given threshold value.But in reality
In the image acquisition process on border, illumination may change, and the position of image can also have a small amount of deviation, a large amount of caused by offset
Defect pixel point can cover the presence of point, line defect.Therefore, existing surface defects detection system has certain limitation, tool
Have the shortcomings that detection speed is slow, testing cost is high.
Summary of the invention
The object of the present invention is to provide a kind of visual identity defect inspection method based on printed matter character, this method
It is registrated using shape, defects detection is carried out using OCV, difference shadow method, Detection accuracy is high, suitable for general machine
Vision platform.
Invention solves technical solution used by its technical problem: a kind of visual identity defect based on printed matter character
Detection method, characterized by the following steps:
Step 1: it using the image of high speed high-definition camera acquisition standardized product and the image of product to be measured, obtains and corresponds to
ROI region, then divide ROI region image character, obtain the area image of each character；
Step 2: shape matching, the ranks coordinate of the character searched, matching point are carried out to the image of product to be measured
Several and corresponding templates number, if otherwise matching number successively makes the character of search not equal to character number for rejected product
It is detected with OCV detection system, obtains the printing quality score of character；
Step 3: if character printing mass fraction is lower than pre-set Low threshold, as substandard product, terminate this
Detection；It is qualified product if character printing mass fraction is higher than high threshold；Carry out character recognition；If character printing mass fraction exists
Between Low threshold and high threshold, the image character of standard picture character and product to be measured is registrated, to standard picture and production to be measured
The corresponding binary image of the image of product subtracts each other to obtain error image, and feature judges product to be measured with the presence or absence of scarce according to area
It falls into.
Preferably, the ROI image in the step 1 is to require region to be measured.
Preferably, referring to that ROI image carries out Threshold segmentation to ROI image separating character in the step 1, obtain
Then binary image is connected to, obtain the minimum circumscribed rectangle of each character, and the boundary rectangle is amplified certain pixel
Make that it includes backgrounds appropriate, finally by the corresponding image cropping of amplified boundary rectangle, obtains template image, and will obtain
Template image and character correspond with training obtain OCV file.
Preferably, if matching number in step 2 is equal to character number, then successively to the character of search and corresponding mould
The character of plate image is compared, and is detected using OCV detection system, and the printing quality score of the character is obtained.
Preferably, in step 3, if character printing mass fraction between Low threshold and high threshold, by standard picture
The image character of character and product to be measured registration, subtracts each other the corresponding binary image of the image of standard picture and product to be measured
To error image, feature judges product to be measured with the presence or absence of defect according to area.
Advantageous effect of the invention is: the present invention carries out automatic character recognition and defects detection by NI Vision Builder for Automated Inspection, can
Missing inspection erroneous detection caused by human factor is avoided, and cost of labor is greatly reduced, so as to avoid the training of artificial detection bring, pipe
The huge invisible costs such as reason.
Secondly, the present invention is carried out one by one using image character and standard picture character of the shape matching method to product to be measured
Registration, solves the problems, such as point, line defect missing inspection caused by the deviation because of existing for picture position, so that the image word of product to be measured
It accords with and spatially being corresponded with each pixel of standard picture character.
Furthermore the present invention judges judge whether its mass fraction is qualified by OCV first, then to poor shadow using many condition
The defect area and simply connected maximum region that method obtains carry out area extraction, judge whether that qualification, this method mention according to area
High Detection accuracy.
Detailed description of the invention
Fig. 1 is the step schematic diagram of the visual identity defect inspection method of the invention based on printed matter character.
Fig. 2 is the flow chart of the visual identity defect inspection method of the invention based on printed matter character.
Fig. 3 is Character mother plate in the standard picture of the visual identity defect inspection method of the invention based on printed matter character
Figure.
Fig. 4 is the character picture to be measured of the visual identity defect inspection method of the invention based on printed matter character.
Specific embodiment
Invention is described in further detail presently in connection with attached drawing.These attached drawings are simplified schematic diagram, only to show
Meaning mode illustrates the basic structure of invention, therefore it only shows and invents related composition.
As shown, a kind of visual identity defect inspection method based on printed matter character, it is characterised in that: including as follows
Step:
Step 1: it using the image of high speed high-definition camera acquisition standardized product and the image of product to be measured, obtains and corresponds to
ROI region, then divide ROI region image character, obtain the area image of each character；
Step 2: shape matching, the ranks coordinate of the character searched, matching point are carried out to the image of product to be measured
Several and corresponding templates number, if otherwise matching number successively makes the character of search not equal to character number for rejected product
It is detected with OCV detection system, obtains the printing quality score of character；
Step 3: if character printing mass fraction is lower than pre-set Low threshold, as substandard product, terminate this
Detection；It is qualified product if character printing mass fraction is higher than high threshold；Carry out character recognition；If character printing mass fraction exists
Between Low threshold and high threshold, the image character of standard picture character and product to be measured is registrated, to standard picture and production to be measured
The corresponding binary image of the image of product subtracts each other to obtain error image, and feature judges product to be measured with the presence or absence of scarce according to area
It falls into；
ROI image in the step 1 is to require region to be measured.
ROI image, which carries out Threshold segmentation, to be referred to ROI image separating character in the step 1, obtains binary picture
Then picture is connected to, obtain the minimum circumscribed rectangle of each character, and by the boundary rectangle amplify certain pixel make it includes
Background appropriate obtains template image, and the Prototype drawing that will be obtained finally by the corresponding image cropping of amplified boundary rectangle
OCV file is obtained with training as corresponding with character.
If matching number in step 2 is equal to character number, then successively to the word of the character of search and corresponding template image
Symbol is compared, and is detected using OCV detection system, and the printing quality score of the character is obtained.
In step 3, if character printing mass fraction between Low threshold and high threshold, by standard picture character and to
The image character registration for surveying product, subtracts each other to obtain differential chart to the corresponding binary image of the image of standard picture and product to be measured
Picture, feature judges product to be measured with the presence or absence of defect according to area
In the specific implementation, printed matter character recognition and defects detection based on machine vision, process as shown in Figure 1,
Specifically comprise the following steps:
(1) image packed using high definition, high speed camera acquisition no defective product, acquisition ROI image, separating character,
The template image of standard character, then captured in real-time are obtained, the image of online acquisition product packaging to be measured obtains ROI image, segmentation
Character obtains the ROI region of each character；
The region comprising character is cut first, obtains ROI image, it is therefore intended that just for interested in image
Region is handled, speed up processing；
Then Threshold segmentation is carried out to ROI image, obtains binary image.Here quick certainly using " Wellner 1993 "
Threshold method is adapted to, the basic thought of this method is by rectangular pixels around the pixel to assess threshold value, if the pixel
Value is less than the threshold value, then otherwise it is 0 that the value of the pixel, which is 1:
WhereinFor the average value of all pixels in rectangle around the pixel, w, h are the wide height of image.Obtain
Binary image；
Binary image is connected to again, obtains the minimum circumscribed rectangle of each character, and the boundary rectangle is amplified
Certain pixel makes that it includes backgrounds appropriate；
Finally by the corresponding image cropping of amplified boundary rectangle, obtains single Character mother plate image and single character waits for
The image of product is surveyed, as shown in Figure 2.Obtained all template images and character are corresponded and calculate separately each Prototype drawing
The Gray Projection both vertically and horizontally of picture and, for making comparisons with the image of product to be measured.By taking Digital Detecting as an example,
Then obtain 0-9 totally 10 templates and 10 groups of projections and, write-in file simultaneously saves.
(2) shape matching carried out to the image of product to be measured, the ranks coordinate of the character searched, matching score and
Corresponding templates number, then successively the character of search is detected using OCV detection system, obtain the printing quality score of character；
Shape matching is according to the shape of object come drawing template establishment, is then measured by certain measurement criterion between shape
Similitude finally finds in the other positions of same piece image or in other images matching object.Measurement criterion has very much,
Here Hausdorff distance is used, it is a kind of measurement for describing similarity degree between two groups of point sets, and the value is smaller, similarity
It is bigger.If marginal point is T in template, marginal point is E in the image of product to be measured, then the Hausdorff between the two point sets
Distance may be expressed as:
H (T, E)=max (h (T, E), h (E, T))
WhereinThe definition of h (E, T) is similar.Product to be measured is obtained by shape matching
Image in position coordinates, the matching score and corresponding matching template of all characters that search.
Successively calculate the transformation matrix of the template image of each character and the image of product to be measured:
The transformed matrix rotation of the character zone of template image is moved on the image of product to be measured, the word is then calculated
The minimum circumscribed rectangle of symbol and amplify with step (1) identical pixel it is so that it includes background appropriate, the region is corresponding
The image-region of product to be measured cuts to arrive the image with the product to be measured of template image same size.It counts respectively again
The projection horizontally and vertically for calculating the image of the product to be measured projects with the template image saved in step (1) and makees
Comparison, finds out similarity, i.e. mass fraction.
(3) mass fraction obtained according to step (2), a point situation judge whether qualified product
Two quality score thresholds, Low threshold and high threshold are set, it is assumed that are respectively MinT and MaxT.Gross area threshold is set
Value T1 and simply connected area threshold T2.
If mass fraction is less than MinT, it is directly judged to rejected product；
If mass fraction is greater than MaxT, character late judgement is carried out, when all character qualities scores are all larger than MaxT
When, it is judged to qualified product, then carry out character recognition；
If mass fraction between MinT and MaxT, carries out subtracting each other behaviour to the region of template image obtained in step (2)
Make, acquires difference region.Template image region is let R be, S is the image-region of product to be measured, and aforesaid operations indicate are as follows:
T=(R ∪ S)-(R ∩ S)
After obtaining difference region, the gross area Area1 in calculating difference region acquires Dan Lian in addition, difference region is connected to
The logical maximum region Area2 of area, if Area1 > T1 or Area2 > T2, is judged to rejected product.Otherwise it is qualified product, carries out
Character recognition.
The method of character recognition has the methods of matching method, neural network, identifies here to simple characters, such as number identification,
Using matching process, the specific steps are as follows: character position obtained in step (2) sorts by column coordinate, if there is multirow, needs same
When sorted according to ranks coordinate, the also corresponding sequence of corresponding template number thus obtains in every row from left to right each word
Corresponding template number (such as 0-9) is accorded with, that is, identifies character.If neural network side can be used to more complex character recognition
Method.
It is enlightenment with the above-mentioned desirable embodiment according to invention, through the above description, relevant staff is complete
Can without departing from the scope of the technological thought of the present invention', carry out various changes and amendments, this invention it is technical
Range is not limited to the contents of the specification, it is necessary to which the technical scope thereof is determined according to the scope of the claim.
Claims (5)
1. a kind of visual identity defect inspection method based on printed matter character, characterized by the following steps:
Step 1: using the image of high speed high-definition camera acquisition standardized product and the image of product to be measured, the corresponding area ROI is obtained
Domain, then divide ROI region image character, obtain the area image of each character；
Step 2: carrying out shape matching to the image of product to be measured, the ranks coordinate of the character searched, matching score and
Corresponding templates number, for rejected product, otherwise successively uses the character of search if matching number is not equal to character number
The detection of OCV detection system, obtains the printing quality score of character；
Step 3: if character printing mass fraction is lower than pre-set Low threshold, as substandard product, terminate this inspection
It surveys；It is qualified product if character printing mass fraction is higher than high threshold；Carry out character recognition；If character printing mass fraction is low
Between threshold value and high threshold, the image character of standard picture character and product to be measured is registrated, to standard picture and product to be measured
The corresponding binary image of image subtract each other to obtain error image, feature judges product to be measured with the presence or absence of defect according to area.
2. the visual identity defect inspection method according to claim 1 based on printed matter character, it is characterised in that: described
ROI image in step 1 is to require region to be measured.
3. the visual identity defect inspection method according to claim 1 based on printed matter character, it is characterised in that: described
ROI image, which carries out Threshold segmentation, to be referred to ROI image separating character in step 1, binary image is obtained, is then connected
It is logical, obtain the minimum circumscribed rectangle of each character, and the boundary rectangle is amplified certain pixel to make that it includes backgrounds appropriate, most
Afterwards by the corresponding image cropping of amplified boundary rectangle, template image is obtained, and one by one by obtained template image and character
It is corresponding that OCV file is obtained with training.
4. the visual identity defect inspection method according to claim 1 based on printed matter character, it is characterised in that: step
If matching number in two is equal to character number, then is successively compared to the character of search with the character of corresponding template image,
It is detected using OCV detection system, obtains the printing quality score of the character.
5. the visual identity defect inspection method according to claim 1 based on printed matter character, it is characterised in that: in step
In rapid three, if character printing mass fraction between Low threshold and high threshold, by the image of standard picture character and product to be measured
Character registration, subtracts each other to obtain error image, according to area to the corresponding binary image of the image of standard picture and product to be measured
Feature judges product to be measured with the presence or absence of defect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710621394.6A CN109308700A (en) | 2017-07-27 | 2017-07-27 | A kind of visual identity defect inspection method based on printed matter character |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710621394.6A CN109308700A (en) | 2017-07-27 | 2017-07-27 | A kind of visual identity defect inspection method based on printed matter character |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109308700A true CN109308700A (en) | 2019-02-05 |
Family
ID=65201763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710621394.6A Pending CN109308700A (en) | 2017-07-27 | 2017-07-27 | A kind of visual identity defect inspection method based on printed matter character |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109308700A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
| CN110096980A (en) * | 2019-04-20 | 2019-08-06 | 东莞中科蓝海智能视觉科技有限公司 | Character machining identifying system |
| CN110443803A (en) * | 2019-09-02 | 2019-11-12 | 河海大学 | A kind of printed matter picture quality detection method and device |
| 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 |
| CN111060527A (en) * | 2019-12-30 | 2020-04-24 | 歌尔股份有限公司 | Character defect detection method and device |
| CN111242896A (en) * | 2019-12-31 | 2020-06-05 | 电子科技大学 | Color printing label defect detection and quality rating method |
| CN111445458A (en) * | 2020-03-27 | 2020-07-24 | 广东技术师范大学 | Method for detecting printing quality of mobile phone battery label |
| CN111612774A (en) * | 2020-05-22 | 2020-09-01 | 珠海格力智能装备有限公司 | Method and device for determining defect area, storage medium and processor |
| CN111650220A (en) * | 2020-07-15 | 2020-09-11 | 博科视(苏州)技术有限公司 | Vision-based image-text defect detection method |
| CN111860521A (en) * | 2020-07-21 | 2020-10-30 | 西安交通大学 | Method for segmenting distorted code-spraying characters layer by layer |
| CN112557412A (en) * | 2020-12-25 | 2021-03-26 | 无锡歌迪亚自动化科技有限公司 | Automatic code-spraying printing defect detection system and detection method |
| CN112763513A (en) * | 2021-01-26 | 2021-05-07 | 广东奥普特科技股份有限公司 | Character defect detection method |
| 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 |
| CN113063802A (en) * | 2021-03-17 | 2021-07-02 | 深圳市霍克视觉科技有限公司 | Printed label defect detection method and device |
| CN113360278A (en) * | 2021-05-31 | 2021-09-07 | 南昌印钞有限公司 | Banknote similarity evaluation method and system, computer device and readable storage medium |
| CN113450316A (en) * | 2021-06-09 | 2021-09-28 | 广州大学 | Method, system and device for detecting defects of metal surface characters and storage medium |
| CN113506297A (en) * | 2021-09-10 | 2021-10-15 | 南通天成包装有限公司 | Printing data identification method based on big data processing |
| CN113780235A (en) * | 2021-09-24 | 2021-12-10 | 西安闻泰信息技术有限公司 | Icon flaw detection method and system |
| CN113870212A (en) * | 2021-09-24 | 2021-12-31 | 武汉海川彩印有限责任公司 | Visual identification defect detection method based on presswork characters |
| CN114549504A (en) * | 2022-03-01 | 2022-05-27 | 安徽工业技术创新研究院六安院 | Appearance quality detection method based on machine vision |
| CN116309296A (en) * | 2022-12-31 | 2023-06-23 | 中山市天柏包装制品有限公司 | Intelligent detection method and detection system for defects of packaging box |
| CN116612116A (en) * | 2023-07-19 | 2023-08-18 | 天津伍嘉联创科技发展股份有限公司 | Crystal appearance defect detection method based on deep learning image segmentation |
| CN116758531A (en) * | 2023-08-23 | 2023-09-15 | 苏州视谷视觉技术有限公司 | Machine vision system based on deep learning |
| CN117031052A (en) * | 2023-10-09 | 2023-11-10 | 广州市普理司科技有限公司 | Single printed matter front and back vision detection control system |
| CN117173134A (en) * | 2023-09-07 | 2023-12-05 | 北京冬雪数据工程有限公司 | Method and device for detecting printed image |
| CN117292381A (en) * | 2023-11-24 | 2023-12-26 | 杭州速腾电路科技有限公司 | Method for reading serial number of printed circuit board |
| CN117495852A (en) * | 2023-12-29 | 2024-02-02 | 天津中荣印刷科技有限公司 | Digital printing quality detection method based on image analysis |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803244A (en) * | 2016-11-24 | 2017-06-06 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
-
2017
- 2017-07-27 CN CN201710621394.6A patent/CN109308700A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803244A (en) * | 2016-11-24 | 2017-06-06 | 深圳市华汉伟业科技有限公司 | Defect identification method and system |
Non-Patent Citations (2)
| Title |
|---|
| 许敏等: "无标记印刷品质量在线检测方法研究", 《传感器与微系统》 * |
| 项辉宇等: "基于HALCON的字符识别及缺陷检测", 《机电产品开发与创新》 * |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
| CN110096980A (en) * | 2019-04-20 | 2019-08-06 | 东莞中科蓝海智能视觉科技有限公司 | Character machining identifying system |
| CN110443803A (en) * | 2019-09-02 | 2019-11-12 | 河海大学 | A kind of printed matter picture quality detection method and device |
| 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 |
| CN110940670B (en) * | 2019-11-25 | 2023-04-28 | 佛山缔乐视觉科技有限公司 | Machine vision-based flexographic printing label printing first manuscript detection system and implementation method thereof |
| WO2021135605A1 (en) * | 2019-12-30 | 2021-07-08 | 歌尔股份有限公司 | Character defect detection method and device |
| CN111060527A (en) * | 2019-12-30 | 2020-04-24 | 歌尔股份有限公司 | Character defect detection method and device |
| US12002198B2 (en) | 2019-12-30 | 2024-06-04 | Goertek Inc. | Character defect detection method and device |
| CN111242896A (en) * | 2019-12-31 | 2020-06-05 | 电子科技大学 | Color printing label defect detection and quality rating method |
| CN111445458A (en) * | 2020-03-27 | 2020-07-24 | 广东技术师范大学 | Method for detecting printing quality of mobile phone battery label |
| CN111612774A (en) * | 2020-05-22 | 2020-09-01 | 珠海格力智能装备有限公司 | Method and device for determining defect area, storage medium and processor |
| CN111612774B (en) * | 2020-05-22 | 2024-05-03 | 珠海格力智能装备有限公司 | Determination method, determination device, storage medium and processor for defect area |
| CN111650220B (en) * | 2020-07-15 | 2022-08-09 | 博科视(苏州)技术有限公司 | Vision-based image-text defect detection method |
| CN111650220A (en) * | 2020-07-15 | 2020-09-11 | 博科视(苏州)技术有限公司 | Vision-based image-text defect detection method |
| CN111860521A (en) * | 2020-07-21 | 2020-10-30 | 西安交通大学 | Method for segmenting distorted code-spraying characters layer by layer |
| CN111860521B (en) * | 2020-07-21 | 2022-04-22 | 西安交通大学 | Method for segmenting distorted code-spraying characters layer by layer |
| CN112557412A (en) * | 2020-12-25 | 2021-03-26 | 无锡歌迪亚自动化科技有限公司 | Automatic code-spraying printing defect detection system and detection method |
| CN112763513A (en) * | 2021-01-26 | 2021-05-07 | 广东奥普特科技股份有限公司 | Character defect detection method |
| CN112763513B (en) * | 2021-01-26 | 2022-08-12 | 广东奥普特科技股份有限公司 | Character defect detection method |
| CN113063802B (en) * | 2021-03-17 | 2023-10-20 | 深圳市霍克视觉科技有限公司 | Method and device for detecting defects of printed labels |
| CN113063802A (en) * | 2021-03-17 | 2021-07-02 | 深圳市霍克视觉科技有限公司 | Printed label defect detection method and device |
| CN113034488B (en) * | 2021-04-13 | 2024-04-19 | 荣旗工业科技(苏州)股份有限公司 | Visual inspection method for ink-jet printed matter |
| 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 |
| CN113360278B (en) * | 2021-05-31 | 2024-05-03 | 南昌印钞有限公司 | Banknote character evaluation method, system, computer device and readable storage medium |
| CN113360278A (en) * | 2021-05-31 | 2021-09-07 | 南昌印钞有限公司 | Banknote similarity evaluation method and system, computer device and readable storage medium |
| CN113450316A (en) * | 2021-06-09 | 2021-09-28 | 广州大学 | Method, system and device for detecting defects of metal surface characters and storage medium |
| CN113450316B (en) * | 2021-06-09 | 2022-03-22 | 广州大学 | Method, system and device for detecting defects of metal surface characters and storage medium |
| CN113506297A (en) * | 2021-09-10 | 2021-10-15 | 南通天成包装有限公司 | Printing data identification method based on big data processing |
| CN113870212B (en) * | 2021-09-24 | 2024-01-05 | 武汉精严科技有限公司 | Visual identification defect detection method based on printed matter characters |
| CN113870212A (en) * | 2021-09-24 | 2021-12-31 | 武汉海川彩印有限责任公司 | Visual identification defect detection method based on presswork characters |
| CN113780235A (en) * | 2021-09-24 | 2021-12-10 | 西安闻泰信息技术有限公司 | Icon flaw detection method and system |
| CN114549504A (en) * | 2022-03-01 | 2022-05-27 | 安徽工业技术创新研究院六安院 | Appearance quality detection method based on machine vision |
| CN116309296A (en) * | 2022-12-31 | 2023-06-23 | 中山市天柏包装制品有限公司 | Intelligent detection method and detection system for defects of packaging box |
| CN116612116A (en) * | 2023-07-19 | 2023-08-18 | 天津伍嘉联创科技发展股份有限公司 | Crystal appearance defect detection method based on deep learning image segmentation |
| CN116758531B (en) * | 2023-08-23 | 2023-11-03 | 苏州视谷视觉技术有限公司 | Machine vision system based on deep learning |
| CN116758531A (en) * | 2023-08-23 | 2023-09-15 | 苏州视谷视觉技术有限公司 | Machine vision system based on deep learning |
| CN117173134A (en) * | 2023-09-07 | 2023-12-05 | 北京冬雪数据工程有限公司 | Method and device for detecting printed image |
| CN117173134B (en) * | 2023-09-07 | 2024-04-09 | 北京冬雪数据工程有限公司 | Method and device for detecting printed image |
| CN117031052A (en) * | 2023-10-09 | 2023-11-10 | 广州市普理司科技有限公司 | Single printed matter front and back vision detection control system |
| CN117031052B (en) * | 2023-10-09 | 2024-01-09 | 广州市普理司科技有限公司 | Single printed matter front and back vision detection control system |
| CN117292381A (en) * | 2023-11-24 | 2023-12-26 | 杭州速腾电路科技有限公司 | Method for reading serial number of printed circuit board |
| CN117292381B (en) * | 2023-11-24 | 2024-02-27 | 杭州速腾电路科技有限公司 | Method for reading serial number of printed circuit board |
| CN117495852A (en) * | 2023-12-29 | 2024-02-02 | 天津中荣印刷科技有限公司 | Digital printing quality detection method based on image analysis |
| CN117495852B (en) * | 2023-12-29 | 2024-05-28 | 天津中荣印刷科技有限公司 | Digital printing quality detection method based on image analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109308700A (en) | A kind of visual identity defect inspection method based on printed matter character | |
| CN111161243B (en) | Industrial product surface defect detection method based on sample enhancement | |
| CN109724990B (en) | Method for quickly positioning and detecting code spraying area in label of packaging box | |
| CN108562589B (en) | Method for detecting surface defects of magnetic circuit material | |
| CN111080622A (en) | Neural network training method, workpiece surface defect classification and detection method and device | |
| CN111582294A (en) | Method for constructing convolutional neural network model for surface defect detection and application thereof | |
| CN111242896A (en) | Color printing label defect detection and quality rating method | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN108629319B (en) | Image detection method and system | |
| CN102305798A (en) | Method for detecting and classifying glass defects based on machine vision | |
| CN113724231A (en) | Industrial defect detection method based on semantic segmentation and target detection fusion model | |
| CN105354533B (en) | A kind of unlicensed vehicle model recognizing method of bayonet based on bag of words | |
| CN111461133B (en) | Express delivery surface single item name identification method, device, equipment and storage medium | |
| CN103439348A (en) | Remote controller key defect detection method based on difference image method | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN110570422A (en) | Capsule defect visual detection method based on matrix analysis | |
| CN113962929A (en) | Photovoltaic cell assembly defect detection method and system and photovoltaic cell assembly production line | |
| CN115761773A (en) | Deep learning-based in-image table identification method and system | |
| CN114048789A (en) | Winebottle fault detection based on improved Cascade R-CNN | |
| CN112884741B (en) | Printing apparent defect detection method based on image similarity comparison | |
| Duong et al. | Vision inspection system for pharmaceuticals | |
| CN110046618B (en) | License plate recognition method based on machine learning and maximum extremum stable region | |
| CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
| CN112164057A (en) | Qualified label detection method, storage medium and electronic equipment | |
| CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190205 |