CN109975312A - A kind of cigarette bobbin paper quality detection device and method based on machine vision technique - Google Patents
A kind of cigarette bobbin paper quality detection device and method based on machine vision technique Download PDFInfo
- Publication number
- CN109975312A CN109975312A CN201910317880.8A CN201910317880A CN109975312A CN 109975312 A CN109975312 A CN 109975312A CN 201910317880 A CN201910317880 A CN 201910317880A CN 109975312 A CN109975312 A CN 109975312A
- Authority
- CN
- China
- Prior art keywords
- obbbin
- tested
- original image
- template
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/2433—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures for measuring outlines by shadow casting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8829—Shadow projection or structured background, e.g. for deflectometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of cigarette bobbin paper quality detection device based on machine vision technique, the system includes image acquisition device, controller and alarm, gray processing, floor projection are carried out to the obbbin image in interest region first, the multiple calculating such as size comparison, intensity contrast, similitude comparison are carried out again, calculated result is compared with given threshold, certain value is differed by more than, judges that currently tested obbbin has the defects of wrong board, spot, incompleteness.Device and method flexible operation that its body provides, the advantages that display is more intuitive, detection is more accurate, while can unrestricted choice detection algorithm according to field condition.
Description
Technical field
The application that the invention belongs to machine vision techniques in Field of Tobacco, and in particular to one kind is based on machine vision technique
, cigarette bobbin paper online quality control device and method for cigarette machine, for real-time detection cigarette cigarette making and tipping machine in life
Obbbin used in production process whether there is the defects of wrong board, spot, incompleteness.
Background technique
Obbbin is the papery cigarette material that cigarette cigarette is widely used in tobacco business, belongs to special trade industry
Use paper.In recent years, the Integrating Strategy of reform and tobacco brand is deepened constantly to tobacco business with country, tobacco business competition is got over
It is fiercer to come, and each cigarette enterprise all strengthens innovation for survival and development, and cigarette color, cigarette specification be also more and more therewith
Abundant, different cigarette specifications and brand select different obbbins to carry out cigarette.
When producing cigarette, obbbin is transported to rolling up and connecting machine Material Staging Area from warehouse or is transported to volume from Material Staging Area cigarette enterprise
It picks on board, is likely to will lead to the obbbin specification of carrying and plan or the model of online production mismatches.Meanwhile obbbin
In production or in cigarette cigarette, it is possible to will cause incomplete, pollution, fracture etc..Once there is obbbin mistake board, spot, residual
The problems such as lacking, field worker is difficult to find in time, will cause a large amount of defect close cigarette groups and enters the market field, so that serious quality be caused to ask
Topic, damages the corporate image, recovers defect cigarette, also will increase entreprise cost.To prevent to have above-mentioned quality as far as possible from source
Obbbin be used for cigarette cigarette, need in cigarette making and tipping machine install additional obbbin quality detection device, to obbbin carry out quality testing.
Summary of the invention
The purpose of the present invention is to provide a kind of based on machine vision technique, real-time online for the cigarette bobbin paper of cigarette machine
Quality detection device and method are subtracted from the root with solving the problems, such as that existing obbbin defect can not be identified in real time online
The generation of few unqualified cigarette.
In a first aspect, the present invention provides a kind of cigarette bobbin paper quality detection device based on machine vision technique, the system
Including image acquisition device, controller and alarm,
Described image collector, for acquiring the original image of tested obbbin and template obbbin and original image being sent to control
Device;
The controller, for handling to obtain Gray Projection song to collected original image progress gray processing, floor projection
Line;
And the boundary of obbbin is obtained using gradient method, tested obbbin size is determined, if obbbin of the detected value beyond setting
Size threshold range then determines that defect occurs in obbbin specification, then sends warning message to the alarm;
And/or the gray value of the average gray value of the original image of tested obbbin and the original image of template obbbin is carried out pair
Than when range of the gray difference beyond setting, then determining that tested obbbin is defect obbbin, then sending warning message to the report
Alert device;
And/or the similarity distance of the Gray scale projection curve of tested obbbin and template obbbin is calculated,
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the picture of template obbbin drop shadow curve
Plain gray value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, and evaluation is
When 0, show that similitude between the two is maximum;Evaluation is bigger, then shows that similitude between the two is smaller, work as similarity
When lower than threshold value, then determines that tested obbbin is defect obbbin, then send warning message to the alarm;
Alarm, for receiving the warning message and alarming.
Preferably, the image acquisition device includes industrial camera, LED light source and camera lens, by lens mount (9) by mirror
Head (10) is fixed on industrial camera (8).
Second aspect, the present invention provide a kind of cigarette bobbin paper quality determining method based on machine vision technique, this method
Include:
Acquire the original image of tested obbbin and template obbbin;
Gray processing is carried out to collected original image, floor projection handles to obtain Gray scale projection curve;
The boundary of obbbin is obtained using gradient method, determines tested obbbin size, if obbbin size of the detected value beyond setting
Threshold range then determines that defect occurs in obbbin specification;
The average gray value of the original image of tested obbbin and the gray value of the original image of template obbbin are compared, ash is worked as
Range of the difference beyond setting is spent, then determines that tested obbbin is defect obbbin;
The similarity distance of the Gray scale projection curve of tested obbbin and template obbbin is calculated,
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the picture of template obbbin drop shadow curve
Plain gray value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, and evaluation is
When 0, show that similitude between the two is maximum;Evaluation is bigger, then shows that similitude between the two is smaller, work as similarity
When lower than threshold value, then obbbin existing defects are determined.
Preferably, if obbbin existing defects, alarm operation is executed.
The third aspect, the present invention provide a kind of cigarette bobbin paper quality determining method based on machine vision technique, this method
Include:
Acquire the original image of tested obbbin and template obbbin;
Gray processing is carried out to collected original image, floor projection handles to obtain Gray scale projection curve;
The boundary of obbbin is obtained using gradient method, determines tested obbbin size, if obbbin size of the detected value beyond setting
Threshold range then determines that wrong board or incompleteness occurs in obbbin specification, carries out warning note in next step.
Fourth aspect, the present invention provide a kind of cigarette bobbin paper quality determining method based on machine vision technique, this method
Include:
Acquire the original image of tested obbbin and template obbbin;
The average gray value of the original image of tested obbbin and the gray value of the original image of template obbbin are compared, ash is worked as
Range of the difference beyond setting is spent, then determines that tested obbbin is defect obbbin, carries out warning note in next step.
5th aspect, the present invention provide a kind of cigarette bobbin paper quality determining method based on machine vision technique, acquire quilt
Survey the original image of obbbin and template obbbin;
Gray processing is carried out to collected original image, floor projection handles to obtain Gray scale projection curve;
The similarity distance of the Gray scale projection curve of tested obbbin and template obbbin is calculated,
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the picture of template obbbin drop shadow curve
Plain gray value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, and evaluation is
When 0, show that similitude between the two is maximum;Evaluation is bigger, then shows that similitude between the two is smaller, work as similarity
When lower than threshold value, then determines obbbin existing defects, carry out warning note in next step.
Compared with prior art, the invention has the following advantages:
1. the present invention uses machine vision to cigarette bobbin paper quality testing, the obbbin image in interest region is carried out first
Gray processing, floor projection, then carry out the multiple calculating such as size comparison, intensity contrast, similitude comparison, calculated result and setting threshold
Value is compared, and differs by more than certain value, judges that currently tested obbbin has the defects of wrong board, spot, incompleteness.What its body provided
Device and method flexible operation, display is more intuitive, detects the advantages that more accurate, while can according to field condition freely
Select detection algorithm.
2. the obbbin quality testing that the present invention can be used in various cigarette cigarette making and tipping machines currently on the market, not only but also from source
The generation for reducing defect cigarette, greatly reduces waste of material rate, has saved cost, in turn avoids defect cigarette and come into the market to make
At adverse effect.
Detailed description of the invention
Fig. 1 is obbbin quality detection device functional block diagram provided by the invention;
Fig. 2 is the side sectional view of controller provided by the invention;
Fig. 3 is image acquisition device cross-sectional view provided by the invention;
Fig. 4 is image processing operations flow chart provided by the invention;
Fig. 5 is three kinds of cigarette obbbins (a) provided by the invention, (b) and (c) original image schematic diagram;
Fig. 6 is cigarette obbbin image (a) drop shadow curve provided by the invention schematic diagram;
Fig. 7 is cigarette obbbin image (b) drop shadow curve provided by the invention schematic diagram;
Fig. 8 is cigarette obbbin image (c) drop shadow curve provided by the invention schematic diagram;
Fig. 9 is figure (c) and Prototype drawing (a) topography matching result schematic diagram in Fig. 5;
Wherein, in Fig. 2,1- display screen, 2- display screen mounting bracket, 3- case front panel, 4- expansion board, 5- core board,
6- core board cooling fin, 7- case box, 8- motherboard, 9- cable socket, 10- display screen cable (10), in Fig. 3, on 1- shell
Lid, 2- gasket, 3- windowpane, 4- shell, 5- bracket, 6-LED light source, 7- cable socket, 8- industrial camera, 9- lens mount,
10- camera lens.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Below by way of specific embodiment, the present invention is described in detail.
The hardware configuration of image acquisition device provided by the invention, controller and alarm:
In Fig. 1, core board is used for the operation of operating system and upper computer software.Single-chip microcontroller is responsible for executing upper computer software
Control instruction, including light source control, camera triggering etc.;Image acquisition device communication interface is for connecting image capture module, work
The picture of shooting is sent to the control panel in control module by the interface by industry camera;Output driving circuit for single-chip microcontroller to
Cigarette making and tipping machine control system and alarm send rejecting and alarm signal;Input signal Acquisition Circuit acquires external laser sensor
Signal;Control circuit for light source provides constant-current source for LED light source, and controls the on-off of constant-current source;Operator can pass through display screen
It checks the relevant information of system operation, and the relevant parameter of system is set.
In Fig. 2, the motherboard 8 for the cable socket 9 that has been welded is fixed on case box 7 by screw first.Then will
Expansion board 4, core board 5 and core board cooling fin 6 pass through stud after being secured together by screw and are fixed to case box 7
On, core board cooling fin 6 is close to case box 7;Display screen 1 is fixed to case front panel 3 by display screen mounting bracket 2 again
On, display screen 1 and expansion board 4 are connected by display screen cable 10;Finally by screw by case front panel 3 and case box 7
It is secured together.
In Fig. 3, in Fig. 2, camera lens 10 is fixed on industrial camera 8 by lens mount 9.By screw by industrial phase
Machine 8 and LED light source 6 are fixed on bracket 5;Bracket 5 is fixed on shell 4 by screw.By cable by LED light source 6, work
Industry camera 8, cable socket 7 connect together.It is fixed on shell 4 by the locking nut that cable socket 7 carries, in shell
Packing 2 is encrypted between body upper cover 1 and shell 4, is secured together case top lid 1 and shell 4 finally by screw.
Detection device provided by the invention opens light source, acquisition obbbin figure by specified time Separation control image acquisition device
Picture, and image transmitting analyzed to controller, is handled, and sent to cigarette making and tipping machine control system according to processing result corresponding
Signal, cigarette making and tipping machine control system shut down or alarm according to the signal received, in corresponding position, and Field Force is reminded to come
Processing;Specifically, the method and detection method for handling image include the following steps:
As shown in figure 4, industrial camera acquires the original image (colour) of tested cigarette bobbin paper and template roll bending obbbin;
Gray processing, floor projection: the obbbin image for first taking industrial camera successively carries out gray processing, floor projection
Processing, gray processing is that single pass GRAY image is converted to for the obbbin RGB image for taking industrial camera, is improved subsequent
Processing speed;Projection is in order to which two dimensional image is made projective transformation, is the one-dimensional space by the Feature Conversion of obbbin in image
Data characteristics is conducive to obbbin dimensional measurement.
In Fig. 5, figure (a), figure (b), figure (c) are respectively that the original color obbbin image of three kinds of different sizes (is shown in figure
It is shown as black and white view), wherein figure (a) obbbin width is 26.5mm, figure (b) obbbin width is 20.0mm, figure (c) obbbin is incomplete
Place's mean breadth is 24.0mm;
Size real-time detection method: Fig. 6, Fig. 7, Fig. 8 are respectively to figure (a), figure (b), figure (c) original image gray scale in Fig. 5
The drop shadow curve that floor projection obtains is carried out after change, and each discharge plate then can be obtained to floor projection profile lookup with gradient method
The boundary of paper;The size (unit: pixel) of figure (a) is obtained by detecting are as follows: 447-180=267 schemes the size of (b) are as follows: 393-
191=202 schemes the size of (c) are as follows: 416-175=241, and calculate every 10 pixels and correspond to 1mm, if detected value exceeds threshold
It is worth range, then it is assumed that wrong board or incompleteness occurs in obbbin specification;It is understood that threshold range can voluntarily be set.
Intensity contrast real-time detection: Fig. 9 is after the Prototype drawing (a) in Fig. 5 in figure (c) and Fig. 5 carries out gray value matching
Testing result, intensity contrast are mainly based upon grey similarity principle, and multiple detection unit lattice are arranged in detection zone, detection
In the process, the average gray value of each cell in detection zone is calculated in real time.By the average gray and template of each unit lattice
The gray value of image compares, when gray difference within the set range, then assert that tested obbbin is qualified;Conversely, then determining it
For defect obbbin.The average value ranges of pixel included in each junior unit lattice are [0,255], learn unqualified place for convenience
Position, red "×" will be designated as beyond the cell of threshold range with template comparison result difference, as can be seen from Figure 9 in Fig. 5
Figure (c) obbbin be that there are spots for defect obbbin-.
Similitude comparison: the similarity distance of the Gray scale projection curve of tested obbbin image and template image is calculated, two can be used
The difference of two squares of person's grey scale pixel value calculates.When evaluation is 0, show that similitude between the two is maximum;Calculate number
Value is bigger, then shows that similitude between the two is smaller, calculation formula is as follows:
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the picture of template obbbin drop shadow curve
Plain gray value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, according to formula
(1) similarity between tested obbbin and template obbbin can be calculated;When similarity is lower than threshold value, then it is assumed that obbbin, which exists, to be lacked
It falls into;
Defect if it exists, the present invention will execute alarm operation by alarm.
In addition, in the present invention using to image processing algorithm be all field of machine vision maturation algorithms most in use, it is various
These algorithms are all contained in the machine vision algorithm library of open source, developer can call directly.
Detection device and method provided by the invention effectively solve existing obbbin defect problem, reduce do not conform to from the root
The generation of lattice cigarette reduces its negative effect generated to enterprise;It can be largely using this detection device and detection method
Unqualified cigarette caused by due to obbbin defect is reduced, cigarette cigarette quality is effectively raised, reduces the wave of cigarette material
Rate has saved the production cost of enterprise.
Claims (7)
1. a kind of cigarette bobbin paper quality detection device based on machine vision technique, it is characterised in that: the system includes that image is adopted
Storage, controller and alarm,
Described image collector, for acquiring the original image of tested obbbin and template obbbin and original image being sent to controller;
The controller, for carrying out gray processing to collected original image, floor projection handles to obtain Gray scale projection curve;
And the boundary of obbbin is obtained using gradient method, tested obbbin size is determined, if obbbin size of the detected value beyond setting
Threshold range then determines that defect occurs in obbbin specification, then sends warning message to the alarm;
And/or compare the average gray value of the original image of tested obbbin and the gray value of the original image of template obbbin, when
Range of the gray difference beyond setting then determines that tested obbbin is defect obbbin, then sends warning message to the alarm;
And/or the similarity distance of the Gray scale projection curve of tested obbbin and template obbbin is calculated,
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the pixel ash of template obbbin drop shadow curve
Angle value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, when evaluation is 0,
Show that similitude between the two is maximum;Evaluation is bigger, then shows that similitude between the two is smaller, when similarity is lower than
When threshold value, then determines that tested obbbin is defect obbbin, then send warning message to the alarm;
Alarm, for receiving the warning message and alarming.
2. the cigarette bobbin paper quality detection device according to claim 1 based on machine vision technique, it is characterised in that: institute
The image acquisition device stated includes industrial camera, LED light source and camera lens, and camera lens (10) are fixed to industry by lens mount (9)
On camera (8).
3. a kind of cigarette bobbin paper quality determining method based on machine vision technique, it is characterised in that: this method comprises:
Acquire the original image of tested obbbin and template obbbin;
Gray processing is carried out to collected original image, floor projection handles to obtain Gray scale projection curve;
The boundary of obbbin is obtained using gradient method, determines tested obbbin size, if obbbin size threshold of the detected value beyond setting
Range then determines that defect occurs in obbbin specification, then sends warning message to the alarm;
And/or compare the average gray value of the original image of tested obbbin and the gray value of the original image of template obbbin, when
Range of the gray difference beyond setting then determines that tested obbbin is defect obbbin, then sends warning message to the alarm;
And/or the similarity distance of the Gray scale projection curve of tested obbbin and template obbbin is calculated,
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the pixel ash of template obbbin drop shadow curve
Angle value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, when evaluation is 0,
Show that similitude between the two is maximum;Evaluation is bigger, then shows that similitude between the two is smaller, when similarity is lower than
When threshold value, then determine that tested obbbin is defect obbbin.
4. the cigarette bobbin paper quality determining method according to claim 3 based on machine vision technique, it is characterised in that: if
Obbbin existing defects then execute alarm operation.
5. a kind of cigarette bobbin paper quality determining method based on machine vision technique, it is characterised in that: this method comprises:
Acquire the original image of tested obbbin and template obbbin;
Gray processing is carried out to collected original image, floor projection handles to obtain Gray scale projection curve;
The boundary of obbbin is obtained using gradient method, determines tested obbbin size, if obbbin size threshold of the detected value beyond setting
Range then determines that wrong board or incompleteness occurs in obbbin specification, carries out warning note in next step.
6. a kind of cigarette bobbin paper quality determining method based on machine vision technique, it is characterised in that: this method comprises:
Acquire the original image of tested obbbin and template obbbin;
The average gray value of the original image of tested obbbin and the gray value of the original image of template obbbin are compared, gray scale difference is worked as
The different range beyond setting then determines that tested obbbin is defect obbbin, carries out warning note in next step.
7. a kind of cigarette bobbin paper quality determining method based on machine vision technique, it is characterised in that:
Acquire the original image of tested obbbin and template obbbin;
Gray processing is carried out to collected original image, floor projection handles to obtain Gray scale projection curve;
The similarity distance of the Gray scale projection curve of tested obbbin and template obbbin is calculated,
Similarity distance of the Distance (A, B) between Gray scale projection curve A and B, B are the pixel ash of template obbbin drop shadow curve
Angle value, A are the grey scale pixel value of tested obbbin image projection curve, and L is matched pixel gray value number, when evaluation is 0,
Show that similitude between the two is maximum;Evaluation is bigger, then shows that similitude between the two is smaller, when similarity is lower than
When threshold value, then determines obbbin existing defects, carry out warning note in next step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910317880.8A CN109975312A (en) | 2019-04-19 | 2019-04-19 | A kind of cigarette bobbin paper quality detection device and method based on machine vision technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910317880.8A CN109975312A (en) | 2019-04-19 | 2019-04-19 | A kind of cigarette bobbin paper quality detection device and method based on machine vision technique |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109975312A true CN109975312A (en) | 2019-07-05 |
Family
ID=67085375
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910317880.8A Pending CN109975312A (en) | 2019-04-19 | 2019-04-19 | A kind of cigarette bobbin paper quality detection device and method based on machine vision technique |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109975312A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN114583287A (en) * | 2022-01-20 | 2022-06-03 | 广州超音速自动化科技股份有限公司 | Winder equipment adopting 3D line scanning camera and tab folding detection method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102020036A (en) * | 2010-11-02 | 2011-04-20 | 昆明理工大学 | Visual detection method for transparent paper defect of outer package of strip cigarette |
CN105011358A (en) * | 2015-06-12 | 2015-11-04 | 中国电子科技集团公司第四十一研究所 | Dish paper remnant detection apparatus based on machine vision technology |
CN109596631A (en) * | 2018-12-13 | 2019-04-09 | 中国电子科技集团公司第四十研究所 | A kind of cigarette packet seal mistake board detection device and method based on machine vision technique |
-
2019
- 2019-04-19 CN CN201910317880.8A patent/CN109975312A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102020036A (en) * | 2010-11-02 | 2011-04-20 | 昆明理工大学 | Visual detection method for transparent paper defect of outer package of strip cigarette |
CN105011358A (en) * | 2015-06-12 | 2015-11-04 | 中国电子科技集团公司第四十一研究所 | Dish paper remnant detection apparatus based on machine vision technology |
CN109596631A (en) * | 2018-12-13 | 2019-04-09 | 中国电子科技集团公司第四十研究所 | A kind of cigarette packet seal mistake board detection device and method based on machine vision technique |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN111189837B (en) * | 2020-01-08 | 2023-01-13 | 征图新视(江苏)科技股份有限公司 | Cigarette appearance online detection method and device |
CN114583287A (en) * | 2022-01-20 | 2022-06-03 | 广州超音速自动化科技股份有限公司 | Winder equipment adopting 3D line scanning camera and tab folding detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
CN211262493U (en) | Temperature measurement system and temperature measurement main system | |
CN111289538B (en) | PCB element detection system and detection method based on machine vision | |
CN102837406B (en) | Mold monitoring method based on FAST-9 image characteristic rapid registration algorithm | |
CN104168478B (en) | Based on the video image color cast detection method of Lab space and relevance function | |
CN201890600U (en) | Machine vision belt tearing detecting device | |
CN110018172B (en) | Product detection system and method | |
CN106327483A (en) | Detection equipment logo attaching method, system and device | |
CN108333188A (en) | A kind of online apparent visual detection device of battery pole piece | |
CN112395928A (en) | Method for automatically detecting equipment state operation | |
CN109975312A (en) | A kind of cigarette bobbin paper quality detection device and method based on machine vision technique | |
CN111912850A (en) | Slice cigarette debris detecting system based on artificial intelligence | |
CN109596631B (en) | Cigarette packet seal wrong-brand detection device and method based on machine vision technology | |
CN106228541A (en) | The method and device of screen location in vision-based detection | |
CN110335309A (en) | Method and device based on camera positioning robot | |
CN101853393A (en) | Automatic production and automatic learning method of machine vision system detection algorithm | |
CN202826324U (en) | Monitoring device of module of injection molding machine | |
CN106846302B (en) | Detection method for correctly taking tool and examination table based on method | |
CN116253026A (en) | Cigarette appearance detection and discrimination processing system and method for GDX2 packaging equipment | |
CN212354503U (en) | Cigar quality detection system | |
CN108364245A (en) | A kind of anti-cheating management system in examination hall | |
CN205786286U (en) | There is the high spectrum image detecting system of image inverting function | |
CN112858331A (en) | VR screen detection method and detection system | |
CN113284147B (en) | Foreign matter detection method and system based on yellow foreign matter defects | |
CN110196152A (en) | The method for diagnosing faults and system of large-scale landscape lamp group based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190705 |
|
RJ01 | Rejection of invention patent application after publication |