CN103868935A - Cigarette appearance quality detection method based on computer vision - Google Patents

Cigarette appearance quality detection method based on computer vision Download PDF

Info

Publication number
CN103868935A
CN103868935A CN201410051902.8A CN201410051902A CN103868935A CN 103868935 A CN103868935 A CN 103868935A CN 201410051902 A CN201410051902 A CN 201410051902A CN 103868935 A CN103868935 A CN 103868935A
Authority
CN
China
Prior art keywords
cigarette
image
measured
appearance quality
detection method
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
Application number
CN201410051902.8A
Other languages
Chinese (zh)
Inventor
刘勇
张龙
夏营威
张文
高震宇
王澍
刘小东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei Institutes of Physical Science of CAS
Original Assignee
Hefei Institutes of Physical Science of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hefei Institutes of Physical Science of CAS filed Critical Hefei Institutes of Physical Science of CAS
Priority to CN201410051902.8A priority Critical patent/CN103868935A/en
Publication of CN103868935A publication Critical patent/CN103868935A/en
Pending legal-status Critical Current

Links

Abstract

The invention discloses a cigarette appearance quality detection method based on computer vision. The cigarette appearance quality detection method comprises the steps of collecting a sample image in a certain light environment by a computer vision technology, and recognizing a defect type and a corresponding index from a cigarette image through necessary image preprocessing and image analysis, thereby finishing the detection on the cigarette appearance quality. The detection method provided by the invention serves as a new method for measuring appearance quality of to-be-detected cigarettes, is high in automation degree, and is small in personal error.

Description

Cigarette appearance quality detection method based on computer vision
Technical field
The present invention relates to cigarette quality detection method field, be specially a kind of cigarette appearance quality detection method based on computer vision.
Background technology
Cigarette product in process of production, owing to being infected with the reasons such as equipment ink, device friction or mechanical fault, often cause its surface to occur the quality problems such as stain (comprising foreign material, viscose glue, macula lutea, oil stain etc.), hole, steel seal defect (comprise bite, incomplete, color is fuzzy, position excursion, font are not inconsistent etc.), fold, distortion, aberration, all nonproductive deviations that require in cigarette surface that the type problem and other reasons cause are referred to as cigarette Appearance quality defect.Cigarette Appearance quality defect is the remarkable open defect of cigarette product, for controlling this mass defect, and the increasing essential items for inspection using this index as finished cigarettes quality inspection of tobacco productive corporation.This patent, based on computer vision technique, proposes a kind of cigarette appearance quality detection method.
There is photo-electric and image method principle cigarette detector in existing market, only limits to the quality problems such as nominal, scarce of detection in succession, is not proper Appearance quality defect.Really part instrument can detect the cigarette such as steel seal, stain defect, but the type instrument had not both been considered the singularity of cigarette spatial structure, also cannot comprehensive detection goes out all Appearance quality defects of cigarette.
Summary of the invention
The object of this invention is to provide a kind of cigarette appearance quality detection method based on computer vision, the problem existing to solve prior art.
In order to achieve the above object, the technical solution adopted in the present invention is:
Cigarette appearance quality detection method based on computer vision, is characterized in that: comprise the following steps:
(1), Image Acquisition: by cigarette to be measured be placed in the larger measuring table of cigarette color distortion to be measured on, stable, uniformly under lighting environment, obtain the image of cigarette to be measured by single or multiple cameras, and the image collecting be sent to computing machine;
(2), image processing: utilize image processing algorithm in computing machine, the cigarette image to be measured obtaining is carried out to image to be processed early stage, then utilize projection relation to carry out dimension conversion, obtain the expansion planimetric map of part cigarette to be measured, finally, based on cigarette surface information to be measured, obtain the plane outspread drawing of overall cigarette to be measured by image registration, Image Mosaics and image fusion technology;
(3), graphical analysis and identification: the plane outspread drawing of the entirety cigarette to be measured that step (2) is obtained, in computing machine by artificial intelligence and mode identification technology, analyze color, texture, the shape information of cigarette surf zone to be measured and set up model of cognition, and automatic discrimination defect type and parameter index, finally identify the appearance quality of cigarette to be measured.
The described cigarette appearance quality detection method based on computer vision, is characterized in that: in described step (1), each camera is equipped with exclusive lighting source according to condition.
The described cigarette appearance quality detection method based on computer vision, is characterized in that: in described step (2) image process early stage comprise that denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness correction, color conversion, image are cut apart, resolution adjustment, binaryzation, image connectivity, zone marker, profile extract.
The described cigarette appearance quality detection method based on computer vision, is characterized in that: in described step (2), cigarette surface information to be measured refers to cigarette to be measured surface steel seal, character information.
The described cigarette appearance quality detection method based on computer vision, is characterized in that: in described step (3), artificial intelligence and mode identification technology comprise that template matches, Blob analyze, OCR identifies, machine learning.
The described cigarette appearance quality detection method based on computer vision, is characterized in that: in described step (3), the appearance quality of cigarette to be measured refers to stain, hole, steel seal defect, fold, distortion, the aberration of cigarette outward appearance to be measured.
The inventive method is based on computer vision technique, for the cigarette sample image to be measured obtaining under particular light condition, utilize its surface information feature to carry out space projection conversion, obtain cigarette periphery stretch-out view to be measured, again by analyzing the quality index such as stretch-out view rib-loop color, steel seal information, stain size, plication region, product batch number, judge its defect type and grade, thereby comprehensively realize the automatic identification of cigarette quality defect to be measured, mainly comprise Image Acquisition, image processing, graphical analysis and identification.
Principle of work of the present invention is as follows:
The present invention obtains cigarette image information to be measured under specific lighting condition, obtains cigarette image to be measured to be analyzed by Image Pretreatment Algorithm, obtains the plane outspread drawing of complete cigarette through dimension conversion and Image Mosaics.The information such as the color of ultimate analysis cigarette surf zone to be measured, texture, shape, utilize the image recognition technology such as machine learning and pattern-recognition, realize cigarette open defect kind classification to be measured and corresponding index and export.
The detection method that the present invention proposes provides a kind of new measurement means for the mensuration of cigarette Appearance quality defect to be measured, and automaticity is high, personal error is little.
Computer vision technique of the present invention, mainly comprises computer technology, digital imaging technology, image processing techniques, image analysis technology, image measurement technology.This technology is by the testing image of input, and a series of processing processing of process, and information extraction, export the interested information of user, with the object that reaches identification or measure, has intellectuality, efficiency advantages of higher.When the present invention is used for cigarette appearance quality detection, without human intervention, can automatically realize quick, the Measurement accuracy of defect type and corresponding index, solve the practical problems in cigarette appearance quality detection.
Accompanying drawing explanation
Fig. 1 is information processing transmission block diagram.
Fig. 2 is graphical analysis theory diagram.
Embodiment
Cigarette appearance quality detection method based on computer vision, is characterized in that: comprise the following steps:
(1), Image Acquisition: by cigarette to be measured be placed in the larger measuring table of cigarette color distortion to be measured on, stable, uniformly under lighting environment, obtain the image of cigarette to be measured by single or multiple cameras, and the image collecting be sent to computing machine;
(2), image processing: utilize image processing algorithm in computing machine, the cigarette image to be measured obtaining is carried out to image to be processed early stage, then utilize projection relation to carry out dimension conversion, obtain the expansion planimetric map of part cigarette to be measured, finally, based on cigarette surface information to be measured, obtain the plane outspread drawing of overall cigarette to be measured by image registration, Image Mosaics and image fusion technology;
(3), graphical analysis and identification: the plane outspread drawing of the entirety cigarette to be measured that step (2) is obtained, in computing machine by artificial intelligence and mode identification technology, analyze color, texture, the shape information of cigarette surf zone to be measured and set up model of cognition, and automatic discrimination defect type and parameter index, finally identify the appearance quality of cigarette to be measured.
In step (1), each camera is equipped with exclusive lighting source according to condition.
In step (2) image process early stage comprise that denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness correction, color conversion, image are cut apart, resolution adjustment, binaryzation, image connectivity, zone marker, profile extract.
In step (2), cigarette surface information to be measured refers to cigarette to be measured surface steel seal, character information.
In step (3), artificial intelligence and mode identification technology comprise that template matches, Blob analyze, OCR identifies, machine learning.
In step (3), the appearance quality of cigarette to be measured refers to stain, hole, steel seal defect, fold, distortion, the aberration of cigarette outward appearance to be measured.
Technical scheme for a better understanding of the present invention, is further described below with reference to embodiment (accompanying drawing).
Information processing transmission block diagram in the present invention as shown in Figure 1.The image collecting device that CCD camera and supporting light source are this method, is obtained testing sample digital picture and is transferred to the detection software in computing machine by this device, after above-mentioned image algorithm analysis, provides testing result.
Graphical analysis theory diagram in the present invention as shown in Figure 2.Being specifically described as follows of this step: 1) by denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness correction, color conversion, image cut apart, image pre-processing method optimization, enhancing, recovery, the rectification original image information such as resolution adjustment, binaryzation, image connectivity, zone marker, profile extraction; 2) projection relation to plane according to the face of cylinder, the two dimensional image of stretching cigarette, reduction three dimensional practicality is to compressed image detail in two-dimensional imaging process, obtain the unfolded image of part cigarette, finally, based on information such as cigarette surface steel seal, character, rib-loops, obtain the plane outspread drawing of overall cigarette by image registration, Image Mosaics and image fusion technology; 3) utilize the intelligent identification technologies such as template matches, Blob analysis, OCR identification, machine learning, analyze
The characteristic informations such as the color of cigarette stretch-out view surf zone, texture, shape, set up pattern recognition model, and automatic discrimination defect type and parameter index.

Claims (6)

1. the cigarette appearance quality detection method based on computer vision, is characterized in that: comprise the following steps:
(1), Image Acquisition: by cigarette to be measured be placed in the larger measuring table of cigarette color distortion to be measured on, stable, uniformly under lighting environment, obtain the image of cigarette to be measured by single or multiple cameras, and the image collecting be sent to computing machine;
(2), image processing: utilize image processing algorithm in computing machine, the cigarette image to be measured obtaining is carried out to image to be processed early stage, then utilize projection relation to carry out dimension conversion, obtain the expansion planimetric map of part cigarette to be measured, finally, based on cigarette surface information to be measured, obtain the plane outspread drawing of overall cigarette to be measured by image registration, Image Mosaics and image fusion technology;
(3), graphical analysis and identification: the plane outspread drawing of the entirety cigarette to be measured that step (2) is obtained, in computing machine by artificial intelligence and mode identification technology, analyze color, texture, the shape information of cigarette surf zone to be measured and set up model of cognition, and automatic discrimination defect type and parameter index, finally identify the appearance quality of cigarette to be measured.
2. the cigarette appearance quality detection method based on computer vision according to claim 1, is characterized in that: in described step (1), each camera is equipped with exclusive lighting source according to condition.
3. the cigarette appearance quality detection method based on computer vision according to claim 1, is characterized in that: in described step (2) image process early stage comprise that denoising, filtering, distortion correction, curvature of field reduction, cutting, rotation, stretching, brightness correction, color conversion, image are cut apart, resolution adjustment, binaryzation, image connectivity, zone marker, profile extract.
4. the cigarette appearance quality detection method based on computer vision according to claim 1, is characterized in that: in described step (2), cigarette surface information to be measured refers to cigarette to be measured surface steel seal, character information.
5. the cigarette appearance quality detection method based on computer vision according to claim 1, is characterized in that: in described step (3), artificial intelligence and mode identification technology comprise that template matches, Blob analyze, OCR identifies, machine learning.
6. the cigarette appearance quality detection method based on computer vision according to claim 1, is characterized in that: in described step (3), the appearance quality of cigarette to be measured refers to stain, hole, steel seal defect, fold, distortion, the aberration of cigarette outward appearance to be measured.
CN201410051902.8A 2014-02-14 2014-02-14 Cigarette appearance quality detection method based on computer vision Pending CN103868935A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410051902.8A CN103868935A (en) 2014-02-14 2014-02-14 Cigarette appearance quality detection method based on computer vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410051902.8A CN103868935A (en) 2014-02-14 2014-02-14 Cigarette appearance quality detection method based on computer vision

Publications (1)

Publication Number Publication Date
CN103868935A true CN103868935A (en) 2014-06-18

Family

ID=50907699

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410051902.8A Pending CN103868935A (en) 2014-02-14 2014-02-14 Cigarette appearance quality detection method based on computer vision

Country Status (1)

Country Link
CN (1) CN103868935A (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104132945A (en) * 2014-08-12 2014-11-05 武汉华科喻德科技有限公司 On-line surface quality visual inspection device for bar based on optical fiber conduction
CN104142349A (en) * 2014-07-28 2014-11-12 云南省机械研究设计院 Method for detecting heat sealing defects of external packaging transparent film
CN104992449A (en) * 2015-08-06 2015-10-21 西安冉科信息技术有限公司 Information identification and surface defect on-line detection method based on machine visual sense
CN105029691A (en) * 2015-06-02 2015-11-11 国家烟草质量监督检验中心 Three-dimensional reconstruction technique based method for detecting loose ends of cigarettes
CN105354855A (en) * 2015-12-02 2016-02-24 湖南拓达结构监测技术有限公司 High-rise structure appearance detection device and method
CN105728339A (en) * 2016-02-05 2016-07-06 湖北工业大学 Visual automatic detecting system for ceramic cartridge
CN105852202A (en) * 2016-05-04 2016-08-17 成都贝森伟任科技有限责任公司 Loose-end cigarette removing device
CN106952257A (en) * 2017-03-21 2017-07-14 南京大学 A kind of curved surface label open defect detection method based on template matches and Similarity Measure
CN107156902A (en) * 2017-07-07 2017-09-15 南京大树智能科技股份有限公司 A kind of cigarette presentation quality on-line measuring device
CN107886500A (en) * 2017-10-13 2018-04-06 北京邮电大学 A kind of production monitoring method and system based on machine vision and machine learning
CN109003257A (en) * 2018-06-14 2018-12-14 深圳市华汉伟业科技有限公司 A kind of optical character verification method
CN109142393A (en) * 2018-09-03 2019-01-04 佛亚智能装备(苏州)有限公司 A kind of defect classification method, apparatus and system
CN109345513A (en) * 2018-09-13 2019-02-15 红云红河烟草(集团)有限责任公司 A kind of cigarette package defect inspection method with cigarette packet Attitude Calculation
CN109544541A (en) * 2018-11-27 2019-03-29 云南大学 Cigarette apparent flaws detection method and device
CN110169591A (en) * 2019-04-26 2019-08-27 贵州中烟工业有限责任公司 A kind of method of cigarette laser hole detection
CN110403232A (en) * 2019-07-24 2019-11-05 浙江中烟工业有限责任公司 A kind of cigarette quality detection method based on second level algorithm
CN110621984A (en) * 2017-06-26 2019-12-27 美的集团股份有限公司 Method and system for improving quality inspection
CN110658202A (en) * 2019-09-30 2020-01-07 贵州航天云网科技有限公司 Industrial component appearance defect detection method based on deep learning
CN110998225A (en) * 2017-07-31 2020-04-10 尼德克株式会社 Spectacle frame shape measuring device and lens processing device
CN111189837A (en) * 2020-01-08 2020-05-22 征图新视(江苏)科技股份有限公司 Cigarette appearance online detection method and device
CN111972700A (en) * 2019-05-22 2020-11-24 上海烟草集团有限责任公司 Cigarette appearance detection method and device, equipment, system and medium thereof
CN113269758A (en) * 2021-05-28 2021-08-17 浙江中烟工业有限责任公司 Cigarette appearance detection method and test device based on machine vision

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080094625A1 (en) * 2006-09-21 2008-04-24 Philip Morris Usa Inc. Detection of nitrates from tobacco for correlation with the amount of tobacco-specific nitrosamines within the tobacco
CN102275657A (en) * 2010-06-12 2011-12-14 中国科学院沈阳自动化研究所 Device for online visual detection of apparent defects of strip cigarette
CN102436656A (en) * 2011-09-05 2012-05-02 同济大学 Animal-diversity monitoring method based on computer vision
CN102502000A (en) * 2011-10-25 2012-06-20 中国电子科技集团公司第四十一研究所 Method for detecting lack and upending of cigarettes in cigarette packet on basis of machine vision technology
CN102499471A (en) * 2011-10-25 2012-06-20 中国电子科技集团公司第四十一研究所 Cigarette loose-end detection method based on machine vision 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
CN102697176A (en) * 2012-06-23 2012-10-03 常德烟草机械有限责任公司 Cigarette quality on-line detection device and detection method based on machine vision
WO2013059252A1 (en) * 2011-10-17 2013-04-25 R. J. Reynolds Tobacco Company Cigarette package coding system and associated method
CN103385539A (en) * 2013-08-02 2013-11-13 南京文采科技有限责任公司 Single cigarette empty head detection method based on machine vision and special equipment
CN103559504A (en) * 2013-11-04 2014-02-05 北京京东尚科信息技术有限公司 Image target category identification method and device

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080094625A1 (en) * 2006-09-21 2008-04-24 Philip Morris Usa Inc. Detection of nitrates from tobacco for correlation with the amount of tobacco-specific nitrosamines within the tobacco
CN102275657A (en) * 2010-06-12 2011-12-14 中国科学院沈阳自动化研究所 Device for online visual detection of apparent defects of strip cigarette
CN102436656A (en) * 2011-09-05 2012-05-02 同济大学 Animal-diversity monitoring method based on computer vision
WO2013059252A1 (en) * 2011-10-17 2013-04-25 R. J. Reynolds Tobacco Company Cigarette package coding system and associated method
CN102502000A (en) * 2011-10-25 2012-06-20 中国电子科技集团公司第四十一研究所 Method for detecting lack and upending of cigarettes in cigarette packet on basis of machine vision technology
CN102499471A (en) * 2011-10-25 2012-06-20 中国电子科技集团公司第四十一研究所 Cigarette loose-end detection method based on machine vision 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
CN102697176A (en) * 2012-06-23 2012-10-03 常德烟草机械有限责任公司 Cigarette quality on-line detection device and detection method based on machine vision
CN103385539A (en) * 2013-08-02 2013-11-13 南京文采科技有限责任公司 Single cigarette empty head detection method based on machine vision and special equipment
CN103559504A (en) * 2013-11-04 2014-02-05 北京京东尚科信息技术有限公司 Image target category identification method and device

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
张文等: "基于机器视觉的卷烟污点面积测量系统设计", 《传感器与微系统》 *
李飞等: "基于机器视觉的卷烟接装纸测量系统的设计", 《自动化与仪表》 *
王传宇等: "采用全景技术的机器视觉测量玉米果穗考种指标", 《农业工程学报》 *
董浩等: "基于机器视觉技术的烟用包装膜磨损程度测定方法", 《烟草工艺》 *

Cited By (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104142349A (en) * 2014-07-28 2014-11-12 云南省机械研究设计院 Method for detecting heat sealing defects of external packaging transparent film
CN104132945A (en) * 2014-08-12 2014-11-05 武汉华科喻德科技有限公司 On-line surface quality visual inspection device for bar based on optical fiber conduction
CN105029691A (en) * 2015-06-02 2015-11-11 国家烟草质量监督检验中心 Three-dimensional reconstruction technique based method for detecting loose ends of cigarettes
CN104992449B (en) * 2015-08-06 2018-06-19 艾科芯(深圳)智能科技有限公司 Information identification and surface defect online test method based on machine vision
CN104992449A (en) * 2015-08-06 2015-10-21 西安冉科信息技术有限公司 Information identification and surface defect on-line detection method based on machine visual sense
CN105354855A (en) * 2015-12-02 2016-02-24 湖南拓达结构监测技术有限公司 High-rise structure appearance detection device and method
CN105728339A (en) * 2016-02-05 2016-07-06 湖北工业大学 Visual automatic detecting system for ceramic cartridge
CN105728339B (en) * 2016-02-05 2018-07-27 湖北工业大学 A kind of ceramic cartridge vision automatic checkout system
CN105852202A (en) * 2016-05-04 2016-08-17 成都贝森伟任科技有限责任公司 Loose-end cigarette removing device
CN106952257A (en) * 2017-03-21 2017-07-14 南京大学 A kind of curved surface label open defect detection method based on template matches and Similarity Measure
CN106952257B (en) * 2017-03-21 2019-12-03 南京大学 A kind of curved surface label open defect detection method based on template matching and similarity calculation
CN110621984B (en) * 2017-06-26 2021-08-13 美的集团股份有限公司 Method and system for improving quality inspection
CN110621984A (en) * 2017-06-26 2019-12-27 美的集团股份有限公司 Method and system for improving quality inspection
CN107156902A (en) * 2017-07-07 2017-09-15 南京大树智能科技股份有限公司 A kind of cigarette presentation quality on-line measuring device
CN110998225A (en) * 2017-07-31 2020-04-10 尼德克株式会社 Spectacle frame shape measuring device and lens processing device
CN110998225B (en) * 2017-07-31 2022-06-03 尼德克株式会社 Spectacle frame shape measuring device and lens processing device
US11226196B2 (en) 2017-07-31 2022-01-18 Nidek Co., Ltd. Eyeglass frame shape measurement device and lens processing device
CN107886500A (en) * 2017-10-13 2018-04-06 北京邮电大学 A kind of production monitoring method and system based on machine vision and machine learning
CN109003257A (en) * 2018-06-14 2018-12-14 深圳市华汉伟业科技有限公司 A kind of optical character verification method
CN109003257B (en) * 2018-06-14 2020-09-01 深圳市华汉伟业科技有限公司 Optical character verification method
CN109142393A (en) * 2018-09-03 2019-01-04 佛亚智能装备(苏州)有限公司 A kind of defect classification method, apparatus and system
CN109345513A (en) * 2018-09-13 2019-02-15 红云红河烟草(集团)有限责任公司 A kind of cigarette package defect inspection method with cigarette packet Attitude Calculation
CN109345513B (en) * 2018-09-13 2021-06-01 红云红河烟草(集团)有限责任公司 Cigarette package defect detection method with cigarette package posture calculation function
CN109544541A (en) * 2018-11-27 2019-03-29 云南大学 Cigarette apparent flaws detection method and device
CN110169591A (en) * 2019-04-26 2019-08-27 贵州中烟工业有限责任公司 A kind of method of cigarette laser hole detection
CN111972700A (en) * 2019-05-22 2020-11-24 上海烟草集团有限责任公司 Cigarette appearance detection method and device, equipment, system and medium thereof
CN110403232A (en) * 2019-07-24 2019-11-05 浙江中烟工业有限责任公司 A kind of cigarette quality detection method based on second level algorithm
CN110658202A (en) * 2019-09-30 2020-01-07 贵州航天云网科技有限公司 Industrial component appearance defect detection method based on deep learning
CN111189837A (en) * 2020-01-08 2020-05-22 征图新视(江苏)科技股份有限公司 Cigarette appearance online detection method and device
CN113269758A (en) * 2021-05-28 2021-08-17 浙江中烟工业有限责任公司 Cigarette appearance detection method and test device based on machine vision

Similar Documents

Publication Publication Date Title
CN103868935A (en) Cigarette appearance quality detection method based on computer vision
CN110403232B (en) Cigarette quality detection method based on secondary algorithm
CN104063873B (en) A kind of Model For The Bush-axle Type Parts surface defect online test method based on compressed sensing
CN109239076B (en) Sewing stitch defect detection method based on machine vision
CN106556611A (en) Chromatograp defect automatic checkout system and detection method based on machine vision
CN102529019B (en) Method for mould detection and protection as well as part detection and picking
CN106290392A (en) A kind of little micro-bearing surface pitting defects online test method and system thereof
CN109900711A (en) Workpiece, defect detection method based on machine vision
CN206981462U (en) Stamping parts surface defect detection apparatus based on 3D vision
CN104197836A (en) Vehicle lock assembly size detection method based on machine vision
CN102095731A (en) System and method for recognizing different defect types in paper defect visual detection
CN102175692A (en) System and method for detecting defects of fabric gray cloth quickly
CN106383121B (en) It is a kind of can adaptive multi-brand visible detection method and system
CN104483320A (en) Digitized defect detection device and detection method of industrial denitration catalyst
CN106248680A (en) A kind of engine commutator quality detecting system based on machine vision and detection method
CN112268910A (en) Visual detection system and method for cigarette appearance defects
CN110096980A (en) Character machining identifying system
CN105844282A (en) Method for detecting defects of fuel injection nozzle O-Ring through line scanning camera
CN107328781A (en) A kind of columnar product detection method of surface flaw and device based on machine vision
CN104952754A (en) Coated silicon chip sorting method based on machine vision
CN103091330A (en) Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof
CN108844961A (en) A kind of temperature controller case vision detection system and method
CN103900499B (en) Cigarette package poster region area assay method based on computer vision technique
CN107121063A (en) The method for detecting workpiece
CN109579735A (en) Piston ring contour detecting method for identifying and classifying and its device based on machine vision

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into 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: 20140618