CN109816640A - A kind of product method of calibration based on picture comparison - Google Patents
A kind of product method of calibration based on picture comparison Download PDFInfo
- Publication number
- CN109816640A CN109816640A CN201910014861.8A CN201910014861A CN109816640A CN 109816640 A CN109816640 A CN 109816640A CN 201910014861 A CN201910014861 A CN 201910014861A CN 109816640 A CN109816640 A CN 109816640A
- Authority
- CN
- China
- Prior art keywords
- picture
- template
- samples pictures
- sample
- translation
- 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.)
- Granted
Links
Classifications
-
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
本发明提供了一种基于图片对比的产品校验方法，包括如下步骤：对样本模板和批量打印的第一张样本进行扫描，分别得到模板图片和样本图片，且对所述模板图片和所述样本图片分别进行二值化处理；将所述样本图片与所述模板图片进行模板匹配操作；以匹配重合点为基准，将样本图片的对比基准点按照垂直的X方向和Y方向为坐标系进行多尺度平移获得平移样本图片集合；将所述模板图片和所述平移样本图片集合中的每一平移样本图片均共同按照相同的分割位置分割成多张小图片，以分别获得模板分割图片集合和平移样本分割图片集合；将模板分割图片集合与每一个所述平移样本分割图片集合中的同一位置的分割图片分别进行异或操作。The present invention provides a product verification method based on picture comparison, which includes the following steps: scanning a sample template and the first sample printed in batches, obtaining a template picture and a sample picture respectively, and comparing the template picture and the The sample pictures are binarized respectively; the template matching operation is performed on the sample pictures and the template pictures; the matching coincidence points are used as the benchmark, and the comparison reference points of the sample pictures are carried out according to the vertical X direction and the Y direction as the coordinate system. Multi-scale translation obtains a set of translation sample pictures; the template picture and each translation sample picture in the set of translation sample pictures are jointly divided into a plurality of small pictures according to the same segmentation position, so as to obtain the template segmentation picture set and Translate the sample segmented picture set; perform an exclusive OR operation on the template segmented picture set and the segmented pictures at the same position in each of the shifted sample segmented picture sets.
Description
Technical field
The present invention relates to a kind of product methods of calibration based on picture comparison, belong to image processing technology.
Background technique
With economic development, personalized trend is gradually presented in the material requisite of the people, be also proposed to plant produced and is newly wanted
It asks.Past, plant produced are mass produced in a producing line, and are the same products of production.But from now on,
The production requirement of small-scale multi items will be presented.It is labeled on product, the quality certification and nameplate etc., although not being product ontology,
But be also a part as product, need accurate information.For on product ontology and nameplate/label/quality certification etc.
The inconsistent situation of information, will be named as defect ware, so whether nameplate/label/quality certification is correctly also vital.
Currently, preparing according to 2 steps of sample and batch inside factory nameplate/label/quality certification production.Sample is done
After good, will generally there are more people to carry out confirmation signature, to ensure correctness.Then when bulk print, by first of bulk print
It is compared with sample, is still that more people confirm signature.This process causes worker's stress big, and personnel cost is high.In order to
First efficiency compared with sample of raising bulk print, improves the psychosomatic health of worker, proposes and pass through figure
As technology realizes a kind of solution accurately compared.
Summary of the invention
The purpose of the invention is to provide a kind of product method of calibration based on picture comparison.
The technical solution adopted by the present invention is that: it is a kind of based on picture comparison product method of calibration include the following steps:
Step 1: first sample of sample form and bulk print is scanned, template picture and sample are respectively obtained
This picture, and binary conversion treatment is carried out respectively to the template picture and the samples pictures；
Step 2: the samples pictures and the template picture are subjected to template-matching operation, setting matching precision is not small
In 50-90%, if successful match, the matching coincidence point of the samples pictures Yu the template picture is obtained；If matching
It is unsuccessful, then it can not obtain matching coincidence point, suspension processing；
Step 3: on the basis of matching coincidence point, by the comparison datum mark of samples pictures according to vertical X-direction and the side Y
Multiple dimensioned translation is carried out by setting translation scale to for coordinate system, translates samples pictures set, the translation sample graph to obtain
Piece collection is combined into { translation samples pictures 1, translate samples pictures 2, translate samples pictures 3 ..., translate samples pictures N }；
Step 4: each translation samples pictures in the template picture and the translation samples pictures set are common
Multiple small pictures are divided into according to identical division position, to obtain template segmentation picture set and N number of translation sample point respectively
Picture set is cut, the template segmentation picture set is that { template divides picture 1, and template divides picture 2, and template divides picture
3 ..., template divides picture N }；
Step 5: by template obtained in step 4 segmentation picture set and each described translation sample decomposition pictures
The segmentation picture of same position in conjunction carries out xor operation respectively, the pixel that selected pixels value is 1 from xor operation result
The picture of minimum number is as exclusive or result picture.
Preferably, further include following steps after step 5:
Step 6: the segmentation figure in exclusive or result picture and N number of translation sample decomposition picture set that step 5 is obtained
Piece is carried out or is operated according to same position；
Step 7: by or the obtained result picture of operation carry out being spliced to form the first new picture according to division position, and will
The exclusive or result picture that xor operation obtains carries out being spliced to form the second new picture according to division position, is subtracted with the second new picture
The new picture of third is obtained after first new picture；
Step 8: the location information that pixel value in the new picture of third is 1 is fed back to the template picture after binaryzation, that is, is obtained
Obtain the different content of template picture and samples pictures.
Preferably, in step 7, morphological dilations processing is carried out to the first new picture, and is subtracted with the second new picture swollen
The new picture of third is obtained after swollen treated the first new picture.
Preferably, the coefficient of expansion and the size of connected domain in picture are positively correlated, and the coefficient of expansion is according to the size of connected domain
Carry out ladder value.
Preferably, in step 2, the central area ROI and template picture for choosing samples pictures carry out template matching behaviour
Make, and the area of central area ROI is no less than the 1/4 of samples pictures.
The beneficial effects of the present invention are:
The present invention provides a kind of product methods of calibration based on picture comparison to pass through to template picture and samples pictures point
Not carry out after binary conversion treatment, be split, xor operation and/or operation, thus not only can efficiently accurately to the two into
Row matching operation, but also different location can be accurately exported, it improves to specific efficiency and comparison accuracy.
Specific embodiment
To be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, below with reference to
Specific embodiment, the present invention is further explained.
The present invention provides a kind of product method of calibration based on picture comparison, the product verification based on picture comparison
Method is for carrying out matching comparison to first samples pictures of template picture and bulk print, so that it is determined that inscription inside factory
The planographics indicating labels such as board/label/quality certification are not in mistake, thus reduction in the numbers of seconds.
Specifically, a kind of product method of calibration based on picture comparison comprising following steps:
Step 1: first sample of sample form and bulk print is scanned, template picture and sample are respectively obtained
This picture, and binary conversion treatment is carried out respectively to the template picture and the samples pictures；
Step 2: the samples pictures and the template picture are subjected to template-matching operation, setting matching precision is not small
In 50-90%, if successful match, the matching coincidence point of the samples pictures Yu the template picture is obtained；If matching
It is unsuccessful, then it can not obtain matching coincidence point, suspension processing；
Step 3: on the basis of matching coincidence point, by the comparison datum mark of samples pictures according to vertical X-direction and the side Y
Multiple dimensioned translation is carried out by setting translation scale to for coordinate system, translates samples pictures set, the translation sample graph to obtain
Piece collection is combined into { translation samples pictures 1, translate samples pictures 2, translate samples pictures 3 ..., translate samples pictures N }；
Step 4: each translation samples pictures in the template picture and the translation samples pictures set are common
Multiple small pictures are divided into according to identical division position, to obtain template segmentation picture set and N number of translation sample point respectively
Picture set is cut, the template segmentation picture set is that { template divides picture 1, and template divides picture 2, and template divides picture
3 ..., template divides picture N }, translation samples pictures 1 are { to translate samples pictures 1 to divide in the translation sample decomposition picture set
1 is cut, translation samples pictures 1 segmentation 2, translation samples pictures 1 segmentation 3 ..., translation samples pictures 1 divide N }, and so on；
Step 5: by template obtained in step 4 segmentation picture set and each described translation sample decomposition pictures
The segmentation picture of same position in conjunction carries out xor operation respectively, the pixel that selected pixels value is 1 from xor operation result
The picture of minimum number is as exclusive or result picture, such as such as: template divides picture 1 and translation samples pictures 1 segmentation 1 carries out
Xor operation, template divides picture 1 and translation samples pictures 2 segmentation 1 carries out xor operation ..., and template divides picture 1 and translation
Samples pictures N segmentation 1 carries out xor operation, and so on；
Step 6: the segmentation figure in exclusive or result picture and N number of translation sample decomposition picture set that step 5 is obtained
Piece is carried out or is operated according to same position, to guarantee the integrality of comparing result；
Step 7: by or the obtained result picture of operation carry out being spliced to form the first new picture according to division position, and will
The exclusive or result picture that xor operation obtains carries out being spliced to form the second new picture according to division position, is subtracted with the second new picture
The new picture of third is obtained after first new picture；
Step 8: the location information that pixel value in the new picture of third is 1 is fed back to the template picture after binaryzation, that is, is obtained
Obtain the different content of template picture and samples pictures.
It should be noted that the central area ROI and template picture for choosing samples pictures carry out template in step 2
Area with operation, and central area ROI is no less than the 1/4 of samples pictures；It is further preferred that matching precision is not less than 90%,
To improve the accuracy of matching coincidence point selection.
In addition, in step 7, being carried out at morphological dilations to the first new picture to remove the noise problem in picture
Reason, and the new picture of third is obtained after the first new picture after subtracting expansion process with the second new picture.Moreover, the coefficient of expansion and figure
The size of connected domain is positively correlated in piece, and the coefficient of expansion carries out ladder value according to the size of connected domain.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification is applied directly or indirectly in other relevant technical fields,
Similarly it is included within the scope of the present invention.
Claims (5)
1. a kind of product method of calibration based on picture comparison, which comprises the steps of:
Step 1: first sample of sample form and bulk print is scanned, template picture and sample graph are respectively obtained
Piece, and binary conversion treatment is carried out respectively to the template picture and the samples pictures；
Step 2: the samples pictures and the template picture are subjected to template-matching operation, setting matching precision is not less than 50-
90%, if successful match, obtain the matching coincidence point of the samples pictures Yu the template picture；If matching not at
Function can not then obtain matching coincidence point, suspension processing；
Step 3: on the basis of matching coincidence point, it is according to vertical X-direction and Y-direction by the comparison datum mark of samples pictures
Coordinate system carries out multiple dimensioned translation by setting translation scale, translates samples pictures set, the translation samples pictures collection to obtain
It is combined into { translation samples pictures 1, translate samples pictures 2, translate samples pictures 3 ..., translate samples pictures N }；
Step 4: by the template picture and it is described translation samples pictures set in each translation samples pictures jointly according to
Identical division position is divided into multiple small pictures, to obtain template segmentation picture set and N number of translation sample decomposition figure respectively
Piece set, the template segmentation picture set are that { template divides picture 1, and template divides picture 2, and template divides picture 3 ..., mould
Plate divides picture N }；
Step 5: will be in template obtained in step 4 segmentation picture set and each described translation sample decomposition picture set
The segmentation picture of same position carry out xor operation respectively, the pixel quantity that selected pixels value is 1 from xor operation result
Least picture is as exclusive or result picture.
2. it is according to claim 1 it is a kind of based on picture comparison product method of calibration, which is characterized in that step 5 it
After further include following steps:
Step 6: segmentation picture in exclusive or result picture that step 5 is obtained and N number of translation sample decomposition picture set by
It carries out or operates according to same position；
Step 7: by or the obtained result picture of operation according to division position be spliced to form the first new picture, and by exclusive or
It operates obtained exclusive or result picture to carry out being spliced to form the second new picture according to division position, subtracts first with the second new picture
The new picture of third is obtained after new picture；
Step 8: the location information that pixel value in the new picture of third is 1 is fed back to the template picture after binaryzation, i.e. acquisition mould
The different content of plate picture and samples pictures.
3. the product method of calibration according to claim 2 based on picture comparison, it is characterised in that: in step 7,
Morphological dilations processing is carried out to the first new picture, and is obtained after the first new picture after subtracting expansion process with the second new picture
The new picture of third.
4. the product method of calibration according to claim 3 based on picture comparison, it is characterised in that: the coefficient of expansion and figure
The size of connected domain is positively correlated in piece, and the coefficient of expansion carries out ladder value according to the size of connected domain.
5. the product method of calibration according to claim 1 based on picture comparison, it is characterised in that: in step 2,
The central area ROI and template picture for choosing samples pictures carry out template-matching operation, and the area of central area ROI is no less than
The 1/4 of samples pictures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910014861.8A CN109816640B (en) | 2019-01-08 | 2019-01-08 | Product verification method based on picture comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910014861.8A CN109816640B (en) | 2019-01-08 | 2019-01-08 | Product verification method based on picture comparison |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109816640A true CN109816640A (en) | 2019-05-28 |
| CN109816640B CN109816640B (en) | 2023-05-12 |
Family
ID=66604173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910014861.8A Expired - Fee Related CN109816640B (en) | 2019-01-08 | 2019-01-08 | Product verification method based on picture comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816640B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417187A (en) * | 2020-11-25 | 2021-02-26 | 山东浪潮商用系统有限公司 | Multi-picture comparison method based on NFS |
| US20220207739A1 (en) * | 2019-05-20 | 2022-06-30 | Suzhou Microport Orthorecon Co., Ltd. | Methods and systems for entering and verifying product specifications |
| CN116721272A (en) * | 2023-06-21 | 2023-09-08 | 上海勤宽科技有限公司 | Image comparison method, system, electronic device and computer-readable storage medium |
| CN119152175A (en) * | 2024-11-19 | 2024-12-17 | 湖南视觉伟业智能科技有限公司 | Luminance difference-based illicit snapshot image correction method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200204A (en) * | 2014-09-02 | 2014-12-10 | 福建富士通信息软件有限公司 | Picture processing device and method |
| CN106326887A (en) * | 2016-08-29 | 2017-01-11 | 东方网力科技股份有限公司 | Method and device for checking optical character recognition result |
| CN106682698A (en) * | 2016-12-29 | 2017-05-17 | 成都数联铭品科技有限公司 | OCR identification method based on template matching |
| CN107506767A (en) * | 2017-09-22 | 2017-12-22 | 江苏海事职业技术学院 | The method and apparatus of digital adhesion identification in a kind of picture |
-
2019
- 2019-01-08 CN CN201910014861.8A patent/CN109816640B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200204A (en) * | 2014-09-02 | 2014-12-10 | 福建富士通信息软件有限公司 | Picture processing device and method |
| CN106326887A (en) * | 2016-08-29 | 2017-01-11 | 东方网力科技股份有限公司 | Method and device for checking optical character recognition result |
| CN106682698A (en) * | 2016-12-29 | 2017-05-17 | 成都数联铭品科技有限公司 | OCR identification method based on template matching |
| CN107506767A (en) * | 2017-09-22 | 2017-12-22 | 江苏海事职业技术学院 | The method and apparatus of digital adhesion identification in a kind of picture |
Non-Patent Citations (1)
| Title |
|---|
| 凌翔等: "基于模板匹配方法的不均匀照度车牌图像识别", 《重庆交通大学学报(自然科学版)》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220207739A1 (en) * | 2019-05-20 | 2022-06-30 | Suzhou Microport Orthorecon Co., Ltd. | Methods and systems for entering and verifying product specifications |
| CN112417187A (en) * | 2020-11-25 | 2021-02-26 | 山东浪潮商用系统有限公司 | Multi-picture comparison method based on NFS |
| CN116721272A (en) * | 2023-06-21 | 2023-09-08 | 上海勤宽科技有限公司 | Image comparison method, system, electronic device and computer-readable storage medium |
| CN119152175A (en) * | 2024-11-19 | 2024-12-17 | 湖南视觉伟业智能科技有限公司 | Luminance difference-based illicit snapshot image correction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109816640B (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816640A (en) | A kind of product method of calibration based on picture comparison | |
| CN106952250B (en) | Metal plate strip surface defect detection method and device based on fast R-CNN network | |
| CN104685515B (en) | Word reading device and the container inspection for having used the word reading device | |
| CN103439348A (en) | Remote controller key defect detection method based on difference image method | |
| WO2014172345A2 (en) | Fully automated system and method for image segmentation and quality control of protein microarrays | |
| CN105989588B (en) | Special-shaped material cutting image correction method and system | |
| CN108446717A (en) | A kind of board state collection method and system based on image recognition | |
| CN112435041A (en) | Production batch tracking code generation method and device based on quality tracing | |
| CN110533137A (en) | A kind of coding method of printed circuit board retroactive notation | |
| CN112613367A (en) | Bill information text box acquisition method, system, equipment and storage medium | |
| CN106709531B (en) | A method and device for identifying substances used in multi-process matching cigarette materials | |
| CN106093055B (en) | Quality detection method for plural films | |
| CN118967798A (en) | A method, device and storage medium for positioning a bright group of a sub-pixel on a display screen | |
| US7039256B2 (en) | Efficient verification of recognition results | |
| CN105093092B (en) | The method that wafer sort Summary standardization is realized using Excel | |
| CN114648776B (en) | Financial reimbursement data processing method and processing system | |
| CN115862033B (en) | Method and system for performing OCR (optical character recognition) and structuring on physical examination report | |
| CN109410662B (en) | Method and device for manufacturing Chinese character multimedia card | |
| CN112702905B (en) | Backtracking method and system for printed circuit board yield and production equipment error rate | |
| CN115734072B (en) | A method and device for centralized IoT monitoring of industrial automation equipment | |
| CN113888196A (en) | Method and system for implanting traceability information | |
| CN117541542A (en) | Quick and accurate detection method and system for defects of self-adhesive products | |
| CN105044941B (en) | The size detecting method of litho pattern | |
| CN103677474A (en) | High-precision small-piece collaging system for preparing monolithic integrated capacitive touch screen | |
| CN107025669A (en) | A kind of express delivery list singulation method in logistics sorting |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20230512 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |