CN103900499B - Cigarette package poster region area assay method based on computer vision technique - Google Patents
Cigarette package poster region area assay method based on computer vision technique Download PDFInfo
- Publication number
- CN103900499B CN103900499B CN201410069223.3A CN201410069223A CN103900499B CN 103900499 B CN103900499 B CN 103900499B CN 201410069223 A CN201410069223 A CN 201410069223A CN 103900499 B CN103900499 B CN 103900499B
- Authority
- CN
- China
- Prior art keywords
- cigarette package
- measured
- image
- caveat
- poster
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
- Manufacturing Of Cigar And Cigarette Tobacco (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of cigarette package poster region area assay method based on computer vision technique, to be measured cigarette package image is obtained first, and will be processed in cigarette package image to be measured feeding computer, obtain the binary image in caveat region on cigarette package to be measured, again the binary image in caveat region is processed, caveat edges of regions is obtained, yardstick measurement is then carried out to caveat edges of regions, realize determining cigarette package poster region area to be measured.The present invention proposes a kind of method of automatic measurement cigarette package poster region area, the workload and the human error for introducing of manual detection is greatly reduced, is effectively improved accuracy of detection and detection efficiency.
Description
Technical field
The present invention relates to cigarette measuring method field, specially a kind of cigarette package poster based on computer vision technique
Region area assay method.
Background technology
According to《The Framework Convention on Tobacco Control（FCTC）》Require, the poster region area on China's cigarette package accounts for wrapping
The 30% of main visible surface is filled, poster content is marked with written form.《Chinese tobacco controlling planning (2012-2015)》Clearly
Require, will pass through to expand poster area occupied, increase poster font, strengthen the methods such as color contrast, improve conscientiously tobacco danger
Evil alarming effect.With the propulsion of work of honouring an agreement, cigarette package poster region area will be continually changing.Cigarette package poster area
The measurement of domain area, carrying out the work such as cigarette package mark Sources controlling, special examination, supervision and inspection to tobacco business has emphatically
The meaning that wants.
At present tobacco productive corporation and quality supervised department be when cigarette package poster region area is measured, using ruler people
The length and width in work measurement cigarette package poster region, reference area.The method is affected by human factors larger, measurement process
Middle reviewer must reach over to testing sample, easily makes sample produce certain deformation, can also there is error, shadow in reading numerical values
The accuracy of measurement is rung.In addition, for the complex cigarette package of profile, manual measurement are very loaded down with trivial details, detection efficiency is low.
Content of the invention
It is an object of the invention to provide a kind of cigarette package poster region area measure side based on computer vision technique
Method, to solve the problems, such as that efficiency of manual measurement is low, process is loaded down with trivial details, accuracy is low in prior art.
In order to achieve the above object, the technical solution adopted in the present invention is：
Cigarette package poster region area assay method based on computer vision technique, it is characterised in that：Using camera
Cigarette package image to be measured is obtained under specific illumination environment, and will be located in cigarette package image to be measured feeding computer
Reason, the computer cigarette package image to be measured is carried out successively denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation,
Stretching, brightness correction, color conversion, image segmentation, resolution adjustment, after binary conversion treatment, obtain alert on cigarette package to be measured
Show the binary image in language region, then image connectivity, zone marker, contours extract are carried out to the binary image in caveat region
Process, obtain caveat edges of regions, yardstick measurement is then carried out to caveat edges of regions, realize warning cigarette package to be measured
Language region area is determined.
The described cigarette package poster region area assay method based on computer vision technique, it is characterised in that：Adopt
Cigarette package image to be measured is obtained with single or multiple CCD cameras, cigarette package to be measured is placed on bearing glass, CCD camera its
Cigarette package to be measured on alignment lenses bearing glass, arranges ring body around CCD camera camera lens, and inner wall of ring body is provided with multiple
The LED light source of uniform arrangement, builds specific illumination environment by multiple LED light sources.
The present invention utilizes computer vision technique, gathers sample image, through necessary image under certain lighting environment
Pretreatment and graphical analysis, finally realize that cigarette package poster region area is measured.
The present invention proposes a kind of method of automatic measurement cigarette package poster region area, and artificial inspection is greatly reduced
The workload of survey and the human error for introducing, are effectively improved accuracy of detection and detection efficiency.
Description of the drawings
Fig. 1 is the particular flow sheet of information handling step of the present invention.
Fig. 2 is the particular flow sheet of image analysis step of the present invention.
Fig. 3 is measurement structural representation of the present invention.
Specific embodiment
Based on the cigarette package poster region area assay method of computer vision technique, using camera in specific illumination ring
Cigarette package image to be measured is obtained under border, and will be processed in cigarette package image to be measured feeding computer, the computer
Carry out denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness successively to repair to cigarette package image to be measured
Just, color conversion, image segmentation, resolution adjustment, after binary conversion treatment, obtain two of caveat region on cigarette package to be measured
Value image, then image connectivity, zone marker, contour extraction processing are carried out to the binary image in caveat region, warned
Show language edges of regions, yardstick measurement is then carried out to caveat edges of regions, realize to cigarette package poster region area to be measured
Determine.
1 image of cigarette package to be measured is obtained using single or multiple CCD cameras 5, cigarette package to be measured 1 is placed in bearing glass
On 2, cigarette package to be measured 1 on its camera lens 4 alignment bearing glass 2 of CCD camera 5 arranges ring body around CCD camera camera lens 5,
Inner wall of ring body is provided with the LED light source 3 of multiple uniform arrangements, builds specific illumination environment by multiple LED light sources 3.
The inventive method is based on computer vision technique, by obtaining cigarette package image, by poster in analysis of the image
The border in region, so as to realize the measurement of poster region area, i.e., mainly includes image acquisition, graphical analysis.In major technique
Hold as follows：
（1）The digitized video of testing sample is obtained in the present invention by single or multiple cameras.Tobacco shred to be measured or box contain
Caveat surface is placed on bearing glass downwards, and this imaging system is equipped with lighting source.
（2）Image processing algorithm during graphical analysis is referred to using computer in the present invention, after obtaining testing sample image,
Through necessary denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness correction, color conversion, image segmentation,
The process of the image such as resolution adjustment, binaryzation, image connectivity, zone marker, contours extract early stage, then pass through various image procossings
Poster region area is extracted with analysis method.
In order to be better understood from technical scheme, below with reference to embodiment（Accompanying drawing）It is further described.This
A little embodiments are only illustrative of the invention and is not intended to limit the scope of the invention.In addition, it is to be understood that saying the present invention has been read
After the content that awards, those skilled in the art can make various changes and modification to the present invention, and these equivalent form of values equally fall within
The application claims limited range.
The idiographic flow of the information handling step in the present invention is as shown in Figure 1.Image collector of the CCD camera for this method
Put, the digital picture that testing sample can be obtained by the device, the image point of the Digital Image Transmission for collecting to computer
Analysis software.Image analysis software receives digital picture and which is analyzed, and provides recognition result.
The idiographic flow of the image analysis step in the present invention is as shown in Figure 2.The step is specifically described as follows：1）Pass through
Denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness correction, color conversion, image segmentation, resolution ratio
The image pre-processing method optimization such as adjustment, binaryzation, image connectivity, zone marker, contours extract, strengthen, restore, correct original
Image information；2）Poster feature extracting method using multiple computer vision methods and Image Engineering Combination of Methods is to police
Language region area is calculated.
Measurement structure in the present invention is as shown in Figure 3.The structure mainly includes：1 testing sample, 2 bearing glass, 3
LED light source, 4 camera lenses, 5 CCD cameras.
Claims (1)
1. the cigarette package poster region area assay method based on computer vision technique, it is characterised in that：Existed using camera
Cigarette package image to be measured is obtained under specific illumination environment, and will be processed in cigarette package image to be measured feeding computer,
The computer carries out denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, drawing successively to cigarette package image to be measured
Stretch, the conversion of brightness correction, color, image segmentation, resolution adjustment, after binary conversion treatment, obtain warning on cigarette package to be measured
The binary image in language region, then the binary image in caveat region is carried out at image connectivity, zone marker, contours extract
Reason, obtains caveat edges of regions, then carries out yardstick measurement to caveat edges of regions, realizes to cigarette package poster to be measured
Region area is determined；
Cigarette package image to be measured is obtained using single or multiple CCD cameras, cigarette package surface containing caveat to be measured is to underlying
On bearing glass, cigarette package to be measured on CCD camera its alignment lenses bearing glass is arranged around CCD camera camera lens
Ring body, bearing glass are located above ring body, and inner wall of ring body is provided with the LED light source of multiple uniform arrangements, by multiple LED light sources
Build specific illumination environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410069223.3A CN103900499B (en) | 2014-02-27 | 2014-02-27 | Cigarette package poster region area assay method based on computer vision technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410069223.3A CN103900499B (en) | 2014-02-27 | 2014-02-27 | Cigarette package poster region area assay method based on computer vision technique |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103900499A CN103900499A (en) | 2014-07-02 |
| CN103900499B true CN103900499B (en) | 2017-03-15 |
Family
ID=50991969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410069223.3A Expired - Fee Related CN103900499B (en) | 2014-02-27 | 2014-02-27 | Cigarette package poster region area assay method based on computer vision technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103900499B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6683500B2 (en) * | 2016-02-24 | 2020-04-22 | 株式会社ディスコ | Inspection equipment and laser processing equipment |
| CN107507204A (en) * | 2017-07-31 | 2017-12-22 | 征图新视（江苏）科技有限公司 | A kind of method that detection zone is automatically extracted in cigarette bag defects detection |
| CN110243698A (en) * | 2019-06-03 | 2019-09-17 | 绍兴文理学院 | Cut damage area method for rapidly estimating in surface based on structural plane overall process Visualization |
| CN110793436B (en) * | 2019-10-24 | 2021-02-12 | 云南昆船设计研究院有限公司 | Detection method for realizing uniform slitting of irregular cigarette packets and storage medium |
| CN116453099A (en) * | 2023-06-14 | 2023-07-18 | 瑞幸咖啡烘焙(屏南)有限公司 | Automatic detection method, medium and equipment for coffee bean package |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2800304Y (en) * | 2005-04-06 | 2006-07-26 | 北京航空航天大学 | Composite lighting system for mini size on-line high precision vision measure |
| CN101865679A (en) * | 2010-06-18 | 2010-10-20 | 杭州双树科技有限公司 | Plane area measuring method based on digital image technology |
| CN102680498A (en) * | 2012-06-12 | 2012-09-19 | 江西中烟工业有限责任公司南昌卷烟厂 | Method for detecting integrity of concave pattern of cigarette filter tip |
| CN103245307A (en) * | 2013-05-22 | 2013-08-14 | 国家烟草质量监督检验中心 | Detection method suitable for determining hot stamping area of cigarette tipping paper |
| CN103292746A (en) * | 2013-05-22 | 2013-09-11 | 国家烟草质量监督检验中心 | Automatic tobacco tipping paper stamping area measuring device based on computer vision |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3414126B2 (en) * | 1996-05-23 | 2003-06-09 | 日産自動車株式会社 | Bore inner wall defect inspection system |
| JP2003214827A (en) * | 2002-01-29 | 2003-07-30 | Ohbayashi Corp | Method for measuring craze by image processing |
| CN101907453B (en) * | 2010-07-23 | 2012-01-11 | 北京农业信息技术研究中心 | Online measurement method and device of dimensions of massive agricultural products based on machine vision |
-
2014
- 2014-02-27 CN CN201410069223.3A patent/CN103900499B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2800304Y (en) * | 2005-04-06 | 2006-07-26 | 北京航空航天大学 | Composite lighting system for mini size on-line high precision vision measure |
| CN101865679A (en) * | 2010-06-18 | 2010-10-20 | 杭州双树科技有限公司 | Plane area measuring method based on digital image technology |
| CN102680498A (en) * | 2012-06-12 | 2012-09-19 | 江西中烟工业有限责任公司南昌卷烟厂 | Method for detecting integrity of concave pattern of cigarette filter tip |
| CN103245307A (en) * | 2013-05-22 | 2013-08-14 | 国家烟草质量监督检验中心 | Detection method suitable for determining hot stamping area of cigarette tipping paper |
| CN103292746A (en) * | 2013-05-22 | 2013-09-11 | 国家烟草质量监督检验中心 | Automatic tobacco tipping paper stamping area measuring device based on computer vision |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器视觉的烟叶面积在线测量;夏营威等;《农业机械学报》;20121031;第43卷(第10期);第168页第2栏第9行至第170页第1栏第2行、第171页第1栏第1行至第2栏第22行 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103900499A (en) | 2014-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103900499B (en) | Cigarette package poster region area assay method based on computer vision technique | |
| CN108918539B (en) | Apparent disease detection device and method for tunnel structure | |
| CN108776140B (en) | Machine vision-based printed matter flaw detection method and system | |
| JP5443435B2 (en) | Tire defect detection method | |
| CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
| CN103868935A (en) | Cigarette appearance quality detection method based on computer vision | |
| CN108109155A (en) | A kind of automatic threshold edge detection method based on improvement Canny | |
| CN102221559A (en) | Online automatic detection method of fabric defects based on machine vision and device thereof | |
| CN103455813A (en) | Method for facula center positioning of CCD image measurement system | |
| CN112330598B (en) | Method, device and storage medium for detecting stiff yarn defects on chemical fiber surface | |
| CN104574353A (en) | Surface defect judgment method based on visual saliency | |
| CN103345743B (en) | A kind of image partition method for battery tail end smart flaw detection | |
| CN104101601B (en) | Surface defect detection apparatus and method | |
| CN111122590B (en) | Ceramic surface defect detection device and detection method | |
| CN107328781A (en) | A kind of columnar product detection method of surface flaw and device based on machine vision | |
| CN102866160B (en) | System and method for detecting surface quality of coin mold | |
| CN107230207A (en) | The detection method and system of tire | |
| CN206223683U (en) | A kind of tabular workpiece with hole surface defect detection apparatus | |
| CN107490583A (en) | A kind of intermediate plate defect inspection method based on machine vision | |
| CN105719275A (en) | Parallel combination image defect segmentation method | |
| CN110310275A (en) | A kind of chain conveyor defect inspection method based on image procossing | |
| CN109341524A (en) | A kind of optical fiber geometric parameter detection method based on machine vision | |
| CN106706644A (en) | Method for detecting lens defects | |
| CN113820319A (en) | Textile surface defect detection device and method | |
| CN103822932A (en) | X-ray real-time image weld defect detection method based on multi-scale filtering operator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170315 Termination date: 20180227 |