CN109377485A - A kind of instant noodles packaging defect machine vision detection method - Google Patents
A kind of instant noodles packaging defect machine vision detection method Download PDFInfo
- Publication number
- CN109377485A CN109377485A CN201811188773.1A CN201811188773A CN109377485A CN 109377485 A CN109377485 A CN 109377485A CN 201811188773 A CN201811188773 A CN 201811188773A CN 109377485 A CN109377485 A CN 109377485A
- Authority
- CN
- China
- Prior art keywords
- image
- instant noodles
- defect
- packaging
- gray
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a kind of instant noodles to pack defect machine vision detection method, specifically includes that and establishes instant noodles packaging automatic defect detecting device model, acquires the instant noodles Packaging image on conveyer belt, pre-process to image, enhance characteristics of image;Image segmentation central pixel point is chosen, similarity measures are established according to the continuity between pixel grey scale, all pixels are divided into different zones;Packaging image is subjected to convolution with Gaussian kernel function and obtains difference of Gaussian image, by asking the gray scale extreme value of image to extract the defect characteristic of instant noodles Packaging image;Classified by measuring the similitude between defect characteristic and sample, detect defect classification and kick and remove, completes the automatic detection of instant noodles packaging defect.This method has preferable stability and robustness, reduces omission factor and false detection rate, improves detection efficiency, and detection speed is fast, realizes non-destructive testing, saves human resources, is enterprise's reduced cost, refines instant noodles packaging more.
Description
Technical field
The present invention relates to food quality inspection, image recognition, art of mathematics, and in particular to a kind of instant noodles packaging defect machine view
Feel detection method.
Background technique
Instant noodles packaging all has a very big impact the appearance and quality of instant noodles, inevitably deposits in print production
In various defects or flaw.More significantly, detection efficiency is low for the labor intensity that existing instant noodles packaging defect detecting device needs,
Easily there is erroneous detection and detection leakage phenomenon in bad adaptability, and testing cost is higher, is not conducive to the reduction of production costs, and weakens instant noodles
Competitiveness.Enterprise without on-line measuring device can only be by way of manually spot-check, and defect detection rate is very low.
Summary of the invention
To solve the above problems, the purpose of the present invention is to provide a kind of convenience with preferable stability and robustness
Bread fills defect machine vision detection method, reduces omission factor and false detection rate, improves detection efficiency, and detection speed is fast, realizes nothing
Damage detection, saves human resources, is enterprise's reduced cost, refines instant noodles packaging more.
The present invention solves the problems, such as technical solution used by it, comprising the following steps:
A. instant noodles packaging automatic defect detecting device model is established, the instant noodles Packaging image on conveyer belt is acquired, it is right
Image is pre-processed, and characteristics of image is enhanced;
B. image segmentation central pixel point is chosen, similarity measures are established according to the continuity between pixel grey scale, it will
All pixels are divided into different zones;
C. Packaging image is subjected to convolution with Gaussian kernel function and obtains difference of Gaussian image, by the gray scale pole for seeking image
Value extracts the defect characteristic of instant noodles Packaging image;
D. classified by measuring the similitude between defect characteristic and sample, detect defect classification and kick and remove, complete
The automatic detection of instant noodles packaging defect.
Further, the step A includes:
(1) instant noodles packaging automatic defect detecting device is established, camera acquires the instant noodles Packaging image on conveyer belt,
It sends master control set to, and image is digitized, equilibrium treatment carried out to the gray value of image using histogram, at equilibrium
Image grayscale after reason are as follows:
Wherein, I is the gray level of image, and f (t) is the probability density function of image grayscale, and t is pixel, to image ash
Degree grade is normalized, then when l ∈ [0,1], probability density function values 1;It otherwise is 0;
(2) if the gray value of image slices vegetarian refreshments (x, y) is g (x, y), tonal range is [g1,g2], it will by mapping function
Gray value is mapped as g'(x, y), carry out greyscale transformation:
Wherein, (α, β) is the tonal range after greyscale transformation.
Further, the step B includes:
(1) to facilitating bread dress image to carry out color space conversion, image is carried out by initialization point by dividing ridge method
It cuts, if some region is Vr, neighborhood Vi(i=1,2 ..., n), then similarity function are as follows:
Wherein, ω is weight coefficient, and n is neighborhood quantity, xiIt is the gray average in each region,It is the ash of all areas
Mean value is spent, obtains a threshold value by maximum variance between clusters, similarity function value is greater than this threshold value, which is chosen as planting
Subregion;
(3) seed region of selection is marked, traverses all seed regions and its neighborhood, if there is region not marked
Note, checks the neighborhood in the region, if neighbourhood signatures are identical, which is similarly marked;If neighbourhood signatures are different, count
The gray average for calculating the region and neighborhood is poor, and the smallest neighborhood of selection differences carries out identical label, traverses all areas, until
All areas are labeled, so that the adjacent pixel for having similar gray-value with seed region is just merged into a region, divide
The scrappy zonule in many of region, setting regions range threshold is poor to gray average by the region merging technique for being less than threshold value
In different the smallest neighborhood, to complete image segmentation.
Further, the step C includes:
(1) Gaussian function of instant noodles Packaging image is constructed:
Wherein, σ is the standard deviation of image normal distribution, and (x, y) is pixel coordinate, (x0,y0) be seed point coordinate,
The then scale space function of image I (x, y) are as follows:
S (x, y)=f (x, y) * I (x, y)
Wherein, * indicates convolution, then σ is smaller, and graphical rule is smaller, and minutia is also just more obvious;
(2) Packaging image generates one group of image by Gaussian function convolution, is divided in scale space by constant k
From obtaining difference of Gaussian function:
D (x, y)=[f (x, y)-f (k (x, y))] * I (x, y)
=S (k (x, y))-S (x, y)
The pixel in image is compared by difference of Gaussian function, sets gray threshold, gray value is found and is greater than
The pixel of threshold value is found gray scale extreme point as characteristic point to be selected in residual pixel point, difference of Gaussian function is carried out safe
Strangle expansion:
Wherein, (x, y)TIt is the offset of pixel, enablesIt, will be in candidate feature point to obtain extreme point
Pixel positioned at edge removes, and extracts stable characteristic point.
Further, the step D includes:
Calculate the Euclidean distance between the characteristic image f (x, y) extracted and detection sample s (x, y):
Wherein, fi(x, y) is ith feature, and n is feature quantity, finds the smallest feature min (d) of Euclidean distance and carries out
Classification, master control set statistical shortcomings type and sending a signal to are kicked except device kick removing, under not having defective packaging that will continue
Procedure, to complete the automatic detection of instant noodles packaging defect.
The beneficial effects of the present invention are:
In the case where instant noodles packaging quality requires higher and higher, the present invention has preferable stability and robustness,
Omission factor and false detection rate are reduced, detection efficiency is improved, detection speed is fast, realizes non-destructive testing, saves human resources, is enterprise
Reduced cost refines instant noodles packaging more.
Detailed description of the invention
Fig. 1 is the overall flow figure that a kind of instant noodles pack defect machine vision detection method;
Fig. 2 fills automatic defect detecting device illustraton of model for convenience of bread;
Fig. 3 fills image deflects feature extraction flow chart for convenience of bread.
Specific embodiment
Referring to Fig.1, method of the present invention the following steps are included:
A. instant noodles packaging automatic defect detecting device model is established, the instant noodles Packaging image on conveyer belt is acquired, it is right
Image is pre-processed, and characteristics of image is enhanced;
(1) instant noodles packaging automatic defect detecting device is established, as shown in Figure 2.Camera acquires the convenience on conveyer belt
Face Packaging image, sends master control set to.There may be various noises for the original image of collection in worksite, it is therefore desirable to be located in advance
Reason.Image is digitized, equilibrium treatment is carried out using gray value of the histogram to image, enhances visual effect.At equilibrium
Image grayscale after reason are as follows:
Wherein, I is the gray level of image, and f (t) is the probability density function of image grayscale, and t is pixel.To image ash
Degree grade is normalized, then when l ∈ [0,1], probability density function values 1;It otherwise is 0.
(2) if the gray value of image slices vegetarian refreshments (x, y) is g (x, y), tonal range is [g1,g2], it will by mapping function
Gray value is mapped as g'(x, y), carry out greyscale transformation:
Wherein, (α, β) is the tonal range after greyscale transformation.To expand the tonal range of image, keep image more clear
It is clear.
B. image segmentation central pixel point is chosen, similarity measures are established according to the continuity between pixel grey scale, it will
All pixels are divided into different zones;
(1) to facilitating bread dress image to carry out color space conversion, image is carried out by initialization point by dividing ridge method
It cuts.If some region is Vr, neighborhood Vi(i=1,2 ..., n), then similarity function are as follows:
Wherein, ω is weight coefficient, and n is neighborhood quantity, xiIt is the gray average in each region,It is the ash of all areas
Spend mean value.A threshold value is obtained by maximum variance between clusters, similarity function value is greater than this threshold value, which is chosen as planting
Subregion.
(2) seed region of selection is marked, traverses all seed regions and its neighborhood.If there is region not marked
Note, checks the neighborhood in the region, if neighbourhood signatures are identical, which is similarly marked;If neighbourhood signatures are different, count
The gray average for calculating the region and neighborhood is poor, and the smallest neighborhood of selection differences carries out identical label.All areas are traversed, until
All areas are labeled.To which the adjacent pixel for having similar gray-value with seed region is just merged into a region.Segmentation
The scrappy zonule in many of region, setting regions range threshold is poor to gray average by the region merging technique for being less than threshold value
In different the smallest neighborhood, to complete image segmentation.
C. Packaging image is subjected to convolution with Gaussian kernel function and obtains difference of Gaussian image, by the gray scale pole for seeking image
Value extracts the defect characteristic (as shown in Figure 3) of instant noodles Packaging image;
(1) Gaussian function of instant noodles Packaging image is constructed:
Wherein, σ is the standard deviation of image normal distribution, and (x, y) is pixel coordinate, (x0,y0) be seed point coordinate.
The then scale space function of image I (x, y) are as follows:
S (x, y)=f (x, y) * I (x, y)
Wherein, * indicates convolution.Then σ is smaller, and graphical rule is smaller, and minutia is also just more obvious.
(2) Packaging image generates one group of image by Gaussian function convolution, is divided in scale space by constant k
From obtaining difference of Gaussian function:
D (x, y)=[f (x, y)-f (k (x, y))] * I (x, y)
=S (k (x, y))-S (x, y)
The pixel in image is compared by difference of Gaussian function, sets gray threshold, gray value is found and is greater than
The pixel of threshold value is found gray scale extreme point as characteristic point to be selected in residual pixel point, difference of Gaussian function is carried out safe
Strangle expansion:
Wherein, (x, y)TIt is the offset of pixel.It enablesTo obtain extreme point.It will be in candidate feature point
Pixel positioned at edge removes, and extracts stable characteristic point.
D. classified by measuring the similitude between defect characteristic and sample, detect defect classification and kick and remove, complete
The automatic detection of instant noodles packaging defect.
Calculate the Euclidean distance between the characteristic image f (x, y) extracted and detection sample s (x, y):
Wherein, fi(x, y) is ith feature, and n is feature quantity.The smallest feature min (d) of Euclidean distance is found to carry out
Classification, master control set statistical shortcomings type and sending a signal to are kicked except device kick removing, under not having defective packaging that will continue
Procedure, to complete the automatic detection of instant noodles packaging defect.
In conclusion just completing a kind of instant noodles packaging defect machine vision detection method of the present invention.The party
Method has preferable stability and robustness, reduces omission factor and false detection rate, improves detection efficiency, and detection speed is fast, realizes nothing
Damage detection, saves human resources, is enterprise's reduced cost, refines instant noodles packaging more.
Claims (5)
1. a kind of instant noodles pack defect machine vision detection method, which comprises the following steps:
A. instant noodles packaging automatic defect detecting device model is established, the instant noodles Packaging image on conveyer belt is acquired, to image
It is pre-processed, enhances characteristics of image;
B. image segmentation central pixel point is chosen, similarity measures are established according to the continuity between pixel grey scale, will be owned
Pixel is divided into different zones;
C. Packaging image is subjected to convolution with Gaussian kernel function and obtains difference of Gaussian image, by asking the gray scale extreme value of image to mention
Take the defect characteristic of instant noodles Packaging image;
D. classified by measuring the similitude between defect characteristic and sample, detect defect classification and kick and remove, it is convenient to complete
The automatic detection of bread dress defect.
2. instant noodles as described in claim 1 pack defect machine vision detection method, which is characterized in that the step A packet
It includes:
(1) instant noodles packaging automatic defect detecting device is established, camera acquires the instant noodles Packaging image on conveyer belt, transmission
It is digitized to master control set, and to image, equilibrium treatment is carried out to the gray value of image using histogram, after equilibrium treatment
Image grayscale are as follows:
Wherein, I is the gray level of image, and f (t) is the probability density function of image grayscale, and t is pixel, to image gray levels
It is normalized, then when l ∈ [0,1], probability density function values 1;It otherwise is 0;
(2) if the gray value of image slices vegetarian refreshments (x, y) is g (x, y), tonal range is [g1,g2], by mapping function by gray scale
Value is mapped as g'(x, y), carry out greyscale transformation:
Wherein, (α, β) is the tonal range after greyscale transformation.
3. instant noodles as claimed in claim 2 pack defect machine vision detection method, which is characterized in that the step B packet
It includes:
(1) to facilitating bread dress image to carry out color space conversion, image is carried out by initialization segmentation by dividing ridge method, if
Some region is Vr, neighborhood Vi(i=1,2 ..., n), then similarity function are as follows:
Wherein, ω is weight coefficient, and n is neighborhood quantity, xiIt is the gray average in each region,Be all areas gray scale it is equal
Value obtains a threshold value by maximum variance between clusters, and similarity function value is greater than this threshold value, which is chosen as seed zone
Domain;
(2) seed region of selection is marked, traverses all seed regions and its neighborhood, if there is region not to be labeled, looked into
See the neighborhood in the region, if neighbourhood signatures are identical, which is similarly marked;If neighbourhood signatures are different, calculating should
The gray average of region and neighborhood is poor, and the smallest neighborhood of selection differences carries out identical label, traverses all areas, until all
Region is labeled, so that the adjacent pixel for having similar gray-value with seed region is just merged into a region, the area of segmentation
The scrappy zonule in many of domain, setting regions range threshold, most to gray average difference by the region merging technique less than threshold value
In small neighborhood, to complete image segmentation.
4. instant noodles as claimed in claim 3 pack defect machine vision detection method, which is characterized in that the step C packet
It includes:
(1) Gaussian function of instant noodles Packaging image is constructed:
Wherein, σ is the standard deviation of image normal distribution, and (x, y) is pixel coordinate, (x0,y0) be seed point coordinate, then scheme
As the scale space function of I (x, y) are as follows:
S (x, y)=f (x, y) * I (x, y)
Wherein, * indicates convolution, then σ is smaller, and graphical rule is smaller, and minutia is also just more obvious;
(2) Packaging image generates one group of image by Gaussian function convolution, is separated, is obtained by constant k in scale space
To difference of Gaussian function:
D (x, y)=[f (x, y)-f (k (x, y))] I (x, y)
=S (k (x, y))-S (x, y)
The pixel in image is compared by difference of Gaussian function, sets gray threshold, gray value is found and is greater than threshold value
Pixel, gray scale extreme point is found in residual pixel point as characteristic point to be selected, difference of Gaussian function is subjected to Taylor's exhibition
It opens:
Wherein, (x, y)TIt is the offset of pixel, enablesTo obtain extreme point, will be located in candidate feature point
The pixel of edge removes, and extracts stable characteristic point.
5. instant noodles as claimed in claim 4 pack defect machine vision detection method, which is characterized in that the step D packet
It includes:
Calculate the Euclidean distance between the characteristic image f (x, y) extracted and detection sample s (x, y):
Wherein, fi(x, y) is ith feature, and n is feature quantity, finds the smallest feature min (d) of Euclidean distance and classifies,
Master control set statistical shortcomings type and sending a signal to is kicked except device kick removing, and does not have defective packaging that will continue lower road work
Sequence, to complete the automatic detection of instant noodles packaging defect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811188773.1A CN109377485B (en) | 2018-10-12 | 2018-10-12 | Machine vision detection method for instant noodle packaging defects |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811188773.1A CN109377485B (en) | 2018-10-12 | 2018-10-12 | Machine vision detection method for instant noodle packaging defects |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109377485A true CN109377485A (en) | 2019-02-22 |
CN109377485B CN109377485B (en) | 2022-09-06 |
Family
ID=65397514
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811188773.1A Active CN109377485B (en) | 2018-10-12 | 2018-10-12 | Machine vision detection method for instant noodle packaging defects |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109377485B (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110415241A (en) * | 2019-08-02 | 2019-11-05 | 同济大学 | A kind of surface of concrete structure quality determining method based on computer vision |
CN110717889A (en) * | 2019-09-06 | 2020-01-21 | 深圳新视智科技术有限公司 | Defect detection method and device based on digital printing, terminal and readable medium |
CN111583084A (en) * | 2020-04-01 | 2020-08-25 | 杭州优视泰信息技术有限公司 | Workpiece defect positioning method |
CN112070710A (en) * | 2019-06-10 | 2020-12-11 | 北京平恒智能科技有限公司 | Method for detecting industrial product defect image |
CN112862760A (en) * | 2021-01-19 | 2021-05-28 | 浙江大学 | Bearing outer ring surface defect area detection method |
CN112862773A (en) * | 2021-01-29 | 2021-05-28 | 山东建筑大学 | Shaving board image defect classification detection method and device |
KR102259519B1 (en) * | 2020-08-28 | 2021-06-03 | 주식회사농심 | cutting error detecting system for pack unti |
KR102278895B1 (en) * | 2020-08-21 | 2021-07-20 | 주식회사농심 | detecting system for packing error |
CN113610851A (en) * | 2021-10-09 | 2021-11-05 | 武汉平桥兄弟包装材料有限公司 | Packaging decoration quality inspection method based on machine vision |
CN113744239A (en) * | 2021-09-02 | 2021-12-03 | 广东奥普特科技股份有限公司 | Soft packet of lithium cell base angle automatic checkout device of polymer based on machine vision |
CN113777033A (en) * | 2021-08-18 | 2021-12-10 | 长沙长泰机器人有限公司 | Raw sliver defect detection method and device based on machine vision |
CN114240888A (en) * | 2021-12-17 | 2022-03-25 | 沭阳安宏木制品厂 | Furniture assembly paint spraying defect repairing method and system based on image processing |
CN114706360A (en) * | 2022-06-06 | 2022-07-05 | 浙江新迪嘉禾食品有限公司 | Bread production quality control method and system |
CN114742788A (en) * | 2022-04-01 | 2022-07-12 | 南通高精数科机械有限公司 | Copper bar defect detection method and system based on machine vision |
CN114813794A (en) * | 2022-02-18 | 2022-07-29 | 成都飞机工业(集团)有限责任公司 | 3D printing nondestructive testing method based on robot |
CN115311289A (en) * | 2022-10-12 | 2022-11-08 | 南通甜享纺织品有限公司 | Method for detecting oil stain defects of plain-color cloth |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009113844A (en) * | 2007-11-08 | 2009-05-28 | Ajinomoto Co Inc | Packaging failure inspection method and apparatus for package product due to frail film |
CN101470896A (en) * | 2007-12-24 | 2009-07-01 | 南京理工大学 | Automotive target flight mode prediction technique based on video analysis |
CN102514767A (en) * | 2011-12-29 | 2012-06-27 | 天津普达软件技术有限公司 | Automatic detection device based on machine vision for defects of instant noodle sauce packets and method |
CN202583085U (en) * | 2011-12-29 | 2012-12-05 | 天津普达软件技术有限公司 | Instant noodles sauce packet defect automatic detection device based on machine vision |
CN103512888A (en) * | 2013-06-05 | 2014-01-15 | 北京化工大学 | Cigarette packet seal defect detecting system based on image identification technology |
CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
US20160258880A1 (en) * | 2015-03-05 | 2016-09-08 | Emage Vision Pte. Ltd. | Inspection of sealing quality in blister packages |
CN107330871A (en) * | 2017-06-29 | 2017-11-07 | 西安工程大学 | The image enchancing method of insulator automatic identification is run under bad weather condition |
CN107481241A (en) * | 2017-08-24 | 2017-12-15 | 太仓安顺财务服务有限公司 | A kind of color image segmentation method based on mixed method |
CN206914796U (en) * | 2017-07-07 | 2018-01-23 | 今麦郎面品有限公司 | A kind of improper packing product remover of instant noodles |
CN108416766A (en) * | 2018-01-31 | 2018-08-17 | 浙江理工大学 | Bilateral incidence type light guide plate defective vision detection method |
-
2018
- 2018-10-12 CN CN201811188773.1A patent/CN109377485B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009113844A (en) * | 2007-11-08 | 2009-05-28 | Ajinomoto Co Inc | Packaging failure inspection method and apparatus for package product due to frail film |
CN101470896A (en) * | 2007-12-24 | 2009-07-01 | 南京理工大学 | Automotive target flight mode prediction technique based on video analysis |
CN102514767A (en) * | 2011-12-29 | 2012-06-27 | 天津普达软件技术有限公司 | Automatic detection device based on machine vision for defects of instant noodle sauce packets and method |
CN202583085U (en) * | 2011-12-29 | 2012-12-05 | 天津普达软件技术有限公司 | Instant noodles sauce packet defect automatic detection device based on machine vision |
CN103512888A (en) * | 2013-06-05 | 2014-01-15 | 北京化工大学 | Cigarette packet seal defect detecting system based on image identification technology |
US20160258880A1 (en) * | 2015-03-05 | 2016-09-08 | Emage Vision Pte. Ltd. | Inspection of sealing quality in blister packages |
CN104794491A (en) * | 2015-04-28 | 2015-07-22 | 重庆大学 | Fuzzy clustering steel plate surface defect detection method based on pre classification |
CN107330871A (en) * | 2017-06-29 | 2017-11-07 | 西安工程大学 | The image enchancing method of insulator automatic identification is run under bad weather condition |
CN206914796U (en) * | 2017-07-07 | 2018-01-23 | 今麦郎面品有限公司 | A kind of improper packing product remover of instant noodles |
CN107481241A (en) * | 2017-08-24 | 2017-12-15 | 太仓安顺财务服务有限公司 | A kind of color image segmentation method based on mixed method |
CN108416766A (en) * | 2018-01-31 | 2018-08-17 | 浙江理工大学 | Bilateral incidence type light guide plate defective vision detection method |
Non-Patent Citations (8)
Title |
---|
KAI PENG等: "Research of Image processing in Instant Noodle Packets Auto-Inspection System", 《2ND INTERNATIONAL CONFERENCE ON ELECTRONIC & MECHANICAL ENGINEERING AND INFORMATION TECHNOLOGY (EMEIT-2012)》 * |
吕建平等: "基于分水岭和种子生长的彩色图像分割", 《西安邮电大学学报》 * |
孔俊等: "基于区域的自动种子区域生长法的彩色图像分割算法", 《东北师大学报(自然科学版)》 * |
王兰英: "基于ARM的泡罩药品包装缺陷检测系统", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
谢丹毅: "药品泡罩包装缺陷机器视觉检测技术的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
陈慧丽等: "基于机器视觉的方便面包装品质检测系统设计", 《包装工程》 * |
陈财彪: "泡罩药品包装缺陷检测中光照处理和图像匹配方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
霍长凡: "桶装面外包装膜缺陷检测系统设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112070710A (en) * | 2019-06-10 | 2020-12-11 | 北京平恒智能科技有限公司 | Method for detecting industrial product defect image |
CN110415241A (en) * | 2019-08-02 | 2019-11-05 | 同济大学 | A kind of surface of concrete structure quality determining method based on computer vision |
CN110717889A (en) * | 2019-09-06 | 2020-01-21 | 深圳新视智科技术有限公司 | Defect detection method and device based on digital printing, terminal and readable medium |
CN111583084A (en) * | 2020-04-01 | 2020-08-25 | 杭州优视泰信息技术有限公司 | Workpiece defect positioning method |
KR102278895B1 (en) * | 2020-08-21 | 2021-07-20 | 주식회사농심 | detecting system for packing error |
KR102259519B1 (en) * | 2020-08-28 | 2021-06-03 | 주식회사농심 | cutting error detecting system for pack unti |
CN112862760B (en) * | 2021-01-19 | 2023-11-10 | 浙江大学 | Bearing outer ring surface defect area detection method |
CN112862760A (en) * | 2021-01-19 | 2021-05-28 | 浙江大学 | Bearing outer ring surface defect area detection method |
CN112862773A (en) * | 2021-01-29 | 2021-05-28 | 山东建筑大学 | Shaving board image defect classification detection method and device |
CN113777033A (en) * | 2021-08-18 | 2021-12-10 | 长沙长泰机器人有限公司 | Raw sliver defect detection method and device based on machine vision |
CN113744239A (en) * | 2021-09-02 | 2021-12-03 | 广东奥普特科技股份有限公司 | Soft packet of lithium cell base angle automatic checkout device of polymer based on machine vision |
CN113610851A (en) * | 2021-10-09 | 2021-11-05 | 武汉平桥兄弟包装材料有限公司 | Packaging decoration quality inspection method based on machine vision |
CN114240888B (en) * | 2021-12-17 | 2022-09-20 | 沭阳安宏木制品厂 | Furniture assembly paint spraying defect repairing method and system based on image processing |
CN114240888A (en) * | 2021-12-17 | 2022-03-25 | 沭阳安宏木制品厂 | Furniture assembly paint spraying defect repairing method and system based on image processing |
CN114813794A (en) * | 2022-02-18 | 2022-07-29 | 成都飞机工业(集团)有限责任公司 | 3D printing nondestructive testing method based on robot |
CN114813794B (en) * | 2022-02-18 | 2023-10-03 | 成都飞机工业(集团)有限责任公司 | Method for acquiring scanning photo required by robot 3D printing nondestructive testing |
CN114742788A (en) * | 2022-04-01 | 2022-07-12 | 南通高精数科机械有限公司 | Copper bar defect detection method and system based on machine vision |
CN114706360A (en) * | 2022-06-06 | 2022-07-05 | 浙江新迪嘉禾食品有限公司 | Bread production quality control method and system |
CN115311289A (en) * | 2022-10-12 | 2022-11-08 | 南通甜享纺织品有限公司 | Method for detecting oil stain defects of plain-color cloth |
Also Published As
Publication number | Publication date |
---|---|
CN109377485B (en) | 2022-09-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109377485A (en) | A kind of instant noodles packaging defect machine vision detection method | |
US20220172348A1 (en) | Information processing device, information processing method, and storage medium | |
CN109961049B (en) | Cigarette brand identification method under complex scene | |
CN115082419B (en) | Blow-molded luggage production defect detection method | |
CN110678901B (en) | Information processing apparatus, information processing method, and computer-readable storage medium | |
CN109191459B (en) | Automatic identification and rating method for continuous casting billet macrostructure center segregation defect | |
CN115082683A (en) | Injection molding defect detection method based on image processing | |
CN103442209B (en) | Video monitoring method of electric transmission line | |
US20210019878A1 (en) | Image processing device, image processing method, and image processing program | |
CN103048329B (en) | A kind of road surface crack detection method based on active contour model | |
CN108830832A (en) | A kind of plastic barrel surface defects detection algorithm based on machine vision | |
CN108181316B (en) | Bamboo strip defect detection method based on machine vision | |
CN114820625B (en) | Automobile top block defect detection method | |
CN104036521A (en) | Novel retina eye fundus image segmenting method | |
CN114897806A (en) | Defect detection method, electronic device and computer readable storage medium | |
KR100601453B1 (en) | Fingerprint recognition method | |
CN110070523A (en) | A kind of foreign matter detecting method for bottom of bottle | |
CN115760820A (en) | Plastic part defect image identification method and application | |
CN110060239A (en) | A kind of defect inspection method for bottle bottleneck | |
CN114782728A (en) | Data visualization method for ground penetrating radar | |
CN111476074A (en) | Human body foreign matter detection method based on millimeter wave image | |
Fang et al. | Towards real-time crack detection using a deep neural network with a Bayesian fusion algorithm | |
CN114067147A (en) | Ship target confirmation method based on local shape matching | |
CN109934817B (en) | Method for detecting malformation of external contour of fruit body | |
CN114550167B (en) | Artificial intelligence based pear quality classification method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220817 Address after: 518000 Room 2107, No. 51, Pingxin North Road, Shangmu Ancient Community, Pinghu Street, Longgang District, Shenzhen, Guangdong, China Applicant after: Shenzhen Zhongzhi Vision Technology Co., Ltd. Address before: 265700 No. 218 Huancheng North Road, Donglai Street, Longkou City, Yantai City, Shandong Province Applicant before: LONGKOU WEIMEISI ENVIRONMENTAL PROTECTION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |