CN109215048A - Pipe tobacco length determining method and system based on machine vision - Google Patents
Pipe tobacco length determining method and system based on machine vision Download PDFInfo
- Publication number
- CN109215048A CN109215048A CN201811109206.2A CN201811109206A CN109215048A CN 109215048 A CN109215048 A CN 109215048A CN 201811109206 A CN201811109206 A CN 201811109206A CN 109215048 A CN109215048 A CN 109215048A
- Authority
- CN
- China
- Prior art keywords
- pipe tobacco
- image
- length
- tested
- area
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of pipe tobacco length determining method and system based on machine vision, the method comprising the steps of: obtaining the camera image of tested pipe tobacco；The camera image of tested pipe tobacco is pre-processed, bianry image is converted to；The area of each connected region in the bianry image of tested pipe tobacco is calculated, and the connected region that area is less than the area threshold of setting is rejected, Retention area is more than or equal to the connected region of the area threshold；Seek the minimum circumscribed rectangle of the connected region retained；The image length of tested pipe tobacco is sought according to minimum circumscribed rectangle, and according to the ratio data of the image length of master sample and physical length, the image length of tested pipe tobacco is scaled physical length.By the method for the invention and system, the length of pipe tobacco can be accurately determined out.
Description
Technical field
The present invention relates to technical field of tobacco, and in particular to a kind of pipe tobacco length determining method based on machine vision and
System.
Background technique
Tobacco structure has a great impact to the releasing content of coke tar of cigarette smoke and tobacco fill value etc., and the coke of cigarette
Oil and tobacco fill value etc. have extremely important influence to the analysis of cigarette sense organ product, therefore tobacco structure has cigarette quality
Great influence, tobacco structure whether stabilizing influence the stabilization of cigarette quality.
During cigarette primary processing, after cut width determines, so-called tobacco structure is primarily referred to as different length tobacco quality
Shared ratio.Have and studies the whole aesthetic quality it has been shown that length>4.75mm pipe tobacco and length<4.00mm pipe tobacco
There are significant differences, are mainly reflected on the aroma quality, miscellaneous gas, the fine and smooth organoleptic indicators such as degree and irritation of flue gas, and
With the reduction of pipe tobacco length, aesthetic quality is totally on a declining curve.In cigarette composition, the otherness of pipe tobacco length be by
What its chemical characteristic was determined.Tobacco leaf or pipe tobacco intrinsic chemical characteristic are the material bases for determining its physical characteristic, multiple beating leaf
Roasting and throwing stage, the poor tobacco leaf of crush resistance and pipe tobacco are easy to happen and make broken phenomenon, formed lesser cigarette of area and
The shorter pipe tobacco of length.Therefore, the chemical component and its aesthetic quality of different size piece cigarettes and different length finished cut tobacco can deposit
In significant difference, to obtain ideal cigarette physical index and its stability, the most probable length of tobacco structure distribution is answered
For 2.00~4.75mm, the pipe tobacco less than 1.40mm should be reduced to the greatest extent.
Existing tobacco structure test separates the pipe tobacco of different length, as a result with each mainly using the method for screening
Mass accumulation on layer or certain layer of sieve accounts for the ratio of gross mass to indicate.The detection method is slightly wide, detects the quantity of pipe tobacco
More and in irregular shape, when pipe tobacco is overlapped, overlapping pipe tobacco separation can not be caused pipe tobacco detection error larger by vibrating sieving machine.
Summary of the invention
To solve above-mentioned deficiency in the prior art, the present invention provides a kind of, and the pipe tobacco length based on machine vision is true
Determine method and system.
To achieve the above objectives, The technical solution adopted by the invention is as follows:
A kind of pipe tobacco length determining method based on machine vision, comprising the following steps:
Step 1, the camera image of tested pipe tobacco is obtained；
Step 2, the camera image of tested pipe tobacco is pre-processed, is converted to bianry image；
Step 3, the area of each connected region in the bianry image of tested pipe tobacco is calculated, and area is less than to the face of setting
The connected region of product threshold value is rejected, and Retention area is more than or equal to the connected region of the area threshold；
Step 4, the minimum circumscribed rectangle of the connected region retained is sought；
Step 5, the image length of tested pipe tobacco is sought according to minimum circumscribed rectangle, and long according to the image of master sample
The ratio data of degree and physical length, is scaled physical length for the image length of tested pipe tobacco.
On the other hand, the present invention also provides a kind of pipe tobacco length based on machine vision to determine system, including with lower die
Block:
Image collection module, for obtaining the camera image of tested pipe tobacco；
Image conversion module is converted to bianry image for pre-processing the camera image of tested pipe tobacco；
Area calculation module, the area of each connected region in the bianry image for calculating tested pipe tobacco, and area is small
It is rejected in the connected region of the area threshold of setting, Retention area is more than or equal to the connected region of the area threshold；
Boundary rectangle seeks module, the minimum circumscribed rectangle of the connected region for seeking retaining；
Length computation module, for seeking the image length of tested pipe tobacco according to minimum circumscribed rectangle, and according to standard sample
The ratio data of image length originally and physical length, is scaled physical length for the image length of tested pipe tobacco.
In another aspect, the present invention also provides a kind of electronic equipment, including memory, processor and it is stored in memory
The step of computer program that is upper and can running on a processor, the processor executes the method for the invention.
In another aspect, it is stored thereon with computer program the present invention also provides a kind of computer readable storage medium,
The step of program realizes the method for the invention when being executed by processor.
Compared with prior art, the invention has the following advantages:
1) this method detects sample using machine vision, the influence so as to avoid manual intervention to detection,
It also avoids screening and detects the big problem of the difficult separation of existing pipe tobacco overlapping, detection error, realize quick, lossless efficient
Detection.
2) pipe tobacco is divided into two class of regular and irregular, with different preprocess method and length calculation method,
And different reference substances has been formulated by a large amount of experiment, the drawbacks of different type pipe tobacco is measured with Same Way is avoided, is
The accuracy of pipe tobacco linear measure longimetry provides guarantee.
3) this method is also applied not only to pipe tobacco measurement of length, while it is long to apply also for other shapes elongated and narrow object
The measurement of degree.
Detailed description of the invention
Fig. 1 shows the supplemental characteristic of the experimental standard sample of linear type pipe tobacco；
Fig. 2 shows the supplemental characteristic of the experimental standard sample of 1/4 round pipe tobacco；
Fig. 3 shows the supplemental characteristic of the experimental standard sample of 1/2 round pipe tobacco；
Fig. 4 shows the supplemental characteristic of the experimental standard sample of S-shaped type pipe tobacco；
Fig. 5 a-b is respectively that regular pipe tobacco pre-processes forward and backward comparison diagram；
Fig. 6 a-d is respectively figure, the filled figure after the original graph of irregular pipe tobacco, filtered figure, corrosion；
Fig. 7 is that regular pipe tobacco rejects image after small area；
Fig. 8 is that irregular pipe tobacco rejects image after small area；
Fig. 9 is the external matrix figure of regular pipe tobacco marker number；
Figure 10 is the external matrix figure of irregular pipe tobacco note number；
Figure 11 is the flow chart of the pipe tobacco length determining method based on machine vision.
Figure 12 is the functional block diagram that system is determined based on the pipe tobacco length of machine vision.
Figure 13 is the functional block diagram of electronic equipment described in embodiment.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but be merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Please refer to Fig. 1-4, respectively show the master sample of regular pipe tobacco data and irregular pipe tobacco master sample
Data, since pipe tobacco has different shape, using the linear type master sample of PS technology film production rule pipe tobacco, irregularly
The 1/2 of pipe tobacco is round, 1/4 round, S-shaped type master sample, i.e. 4 master samples of different shapes, each shape 10 is not
With the sample of size.By the way that the adjustment of 10 samples of each shape is disposed vertically, is horizontally arranged, the right oblique 45 degree placements of sample,
Left oblique 45 degree of placements of sample etc. are utilized respectively following rule detection methods of the invention, anormal detection method (executes step 1 to arrive
Step 6 only calculates image length in step 6) detection 10 times is repeated, by 10 samples of each shape respectively at 10
Different location detection as a result, the average image length of 10 samples 10 positions of each shape is calculated, for linear type
Master sample re-records the actual (tube) length of each master sample using the average image length as the image length of the master sample
The parameters such as degree, for irregular master sample, using 10 samples of 3 shapes 10 positions the average image length as
The image length of the master sample re-records the parameters such as the physical length of each master sample, as shown in Figs 1-4.
Can be refering to Fig. 5-11, a kind of pipe tobacco length determining method based on machine vision provided in the present embodiment, packet
Include following steps:
Step 1 obtains the image of tested pipe tobacco.In the present embodiment, 10 tested pipe tobaccos are placed on obturator sample
Product placement region, by resolution ratio 1292 (H) * 964 (V), the area array cameras of frame frequency 43fps scans pipe tobacco, is converted into image letter
Number, image processing software is transferred to by Ethernet.
In the present embodiment, pipe tobacco is divided into regular pipe tobacco and irregular pipe tobacco, wherein regular pipe tobacco, which refers to, is projected as straight line
Pipe tobacco, irregular pipe tobacco refer to the pipe tobacco for being projected as non-rectilinear (such as 1/2 is round, 1/4 round, S type).
Step 2 pre-processes the image of acquisition, handles as bianry image.
In this step, different pretreatment modes is respectively adopted for regular pipe tobacco and irregular pipe tobacco, specifically such as
Under:
It is directed to regular pipe tobacco: coloring image into logic matrix, i.e., all convert the pixel of color image
One color threshold p, such as 95 are defined according to the wave lower position of grey level histogram at Logical data type, color is big
Pixel in 95 is wholly converted into 1, and color is black, that is, background, other pixels are converted to 0, and color is that white is cigarette
Silk, image before and after the processing is as shown in Fig. 5 a, Fig. 5 b.
Be directed to irregular pipe tobacco: irregular pipe tobacco image shape is curve, and the simple binary picture that carries out is located in advance
Reason, will lead to and filter out true pipe tobacco image border profile, therefore be pre-processed using following steps:
1. filtering: image obtained in step 1 being carried out Local standard deviation filtering, such as chooses the 3 rank unit squares of 3*3
Battle array, is defined as 0 element for the pixel quantity in 3 rank fields in image, the pixel quantity for being unable to designated field is defined as 1 member
Element.
The standard deviation of the method for seeking Hessian matrix using the second dervative of Gaussian convolution core, Gaussian function indicates convolution
Scale, gaussian filtering be according to Gaussian function at certain point and its surrounding pixel set weight, weighting be averaging.So false
If convolution scale ratio pipe tobacco width is much larger, then obtained convolution results will be dragged down at background, because of the ash at background
It is lesser for spending change of gradient, and when convolution scale ratio pipe tobacco width is much smaller, no matter noise or boxed area all can
Retained by filter, therefore the garbages such as noise can be filtered out using the above method.
2. corrosion: one reasonable corrosion structure object window of creation, such as the window that disc radius is 2, after filtering
Image gradually corroded, the boundary for eliminating image has some small and meaningless pixel.
3. refinement: the image after excessive erosion, under conditions of not changing the basic structure of image, by all objects
Continuous lines are all simplified to, the elementary contour of image is retained.
4. Contour filling: being filled to the profile diagram after refinement, the region in lines is all changed to white, pixel
It is wholly converted into 0, i.e. pipe tobacco information, the region outside lines is changed to black, and pixel is wholly converted into 1.Entire preprocessing process
Comparison diagram as shown in Fig. 6 a-d.
Step 3 calculates the area of bianry image obtained in step 2, i.e., the pixel that pixel is 0 in bianry image
Number.For example, the connection n of one n*n of creation ties up unit matrix, such as 3 dimension connected region matrixes of 8 neighborhoods, 8- neighborhood
It is to say a pixel, if connected with other pixels in upper and lower, left and right, the upper left corner, the lower left corner, the upper right corner or the lower right corner
, then it is assumed that they are connection, and visually apparently, the point to communicate with each other forms a region, and disconnected dot
It is 0 by the pixel definition in the region of connection, i.e., the label of white pixel (target), allows in bianry image at different regions
Each individually connected region forms an identified block, and calculates the area of the i.e. each connected region of each home block.
A piece pipe tobacco is that multiple neighborhoods are formed, one connected region of every pipe tobacco.
Step 4, since image and background are not two single levels, useless information is treated as in binary picture
Target point is marked as 1, forms small bianry image area, needs the area useless to these to reject, due to garbage
Point is more, avoids weeding out useful information, therefore define a reasonable connected region area threshold, such as 200, by area
Connected region less than 200 is rejected.
Remaining connected region area is converted into connected region pixel by step 5, i.e., after rejecting small area image
Every pipe tobacco bianry image, take 8- connection matrix, to belong to the same pixel connected region all pixels point distribute phase
Same number, distributes different numbers to the pixel connected region for belonging to different, according to the pixels of different number labels, meter
Calculate the minimum circumscribed rectangle of each pixel connected region.Regular pipe tobacco label is as shown in fig. 7, irregular pipe tobacco label such as figure
Shown in 8.
Step 6 calculates the length of tested pipe tobacco, and being directed to regular pipe tobacco and irregular pipe tobacco has different calculating sides
Method is specifically, as follows:
For regular pipe tobacco: the minimum circumscribed rectangle length of each not isolabeling is the image length of every pipe tobacco, due to
Image length is not the physical length of pipe tobacco, therefore further according to image length and actual (tube) length in the master sample of regular pipe tobacco
Ratio data relationship between degree, converses the physical length of every tested pipe tobacco.
For irregular pipe tobacco: the quantity of pixel shared by every tested pipe tobacco in bianry image is calculated, according to irregular
The data of the master sample of pipe tobacco, calculate the corresponding physical length of each pixel, then after being fitted center line to pipe tobacco, thus
Calculate the sum of each length on center line, the actual length of as tested pipe tobacco.Specific formula is as follows:
Y=x1+x2+x3+ ...+xm-2+xm-1+xm；
Wherein, y is the actual length of tested pipe tobacco；X is the corresponding physical length of each pixel；M is every tested cigarette
The quantity of pixel shared by silk.
Figure 12 is please referred to, identical inventive concept is based on, additionally provides a kind of cigarette based on machine vision in the present embodiment
Filament length degree determines system, comprises the following modules:
Image collection module, for obtaining the camera image of tested pipe tobacco；
Image conversion module is converted to bianry image for pre-processing the camera image of tested pipe tobacco；
Area calculation module, the area of each connected region in the bianry image for calculating tested pipe tobacco, and area is small
It is rejected in the connected region of the area threshold of setting, Retention area is more than or equal to the connected region of the area threshold；
Boundary rectangle seeks module, the minimum circumscribed rectangle of the connected region for seeking retaining；
Length computation module, for seeking the image length of tested pipe tobacco according to minimum circumscribed rectangle, and according to standard sample
The ratio data of image length originally and physical length, is scaled physical length for the image length of tested pipe tobacco.
For the function and concrete processing procedure of modules, the correlation of above-mentioned compression method in embodiment may refer to
Description and attached drawing 5-11, details are not described herein again.
As shown in figure 13, a kind of electronic equipment is provided simultaneously in the embodiment of the present invention, which can be
The equipment that server, computer etc. have data-handling capacity.As shown in figure 13, electronic equipment 100 include: memory 110,
Processor 120 and network module 130.
The memory 110, processor 120 and network module 130 are directly or indirectly electrically connected between each other,
To realize the transmission or interaction of data.The compressibility of adaptive real time spectrum data is stored in memory 110, it is described
The compressibility of adaptive real time spectrum data includes that at least one can be stored in the form of software or firmware (firmware)
Software function module in the memory 110, the software that the processor 120 is stored in memory 110 by operation
Program and module, such as the compressibility of the adaptive real time spectrum data in the embodiment of the present invention, thereby executing various function
It can apply and data processing, i.e. the compression method of adaptive real time spectrum data in the realization embodiment of the present invention.
Wherein, the memory 110 may be, but not limited to, random access memory (Random Access
Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable
Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only
Memory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only
Memory, EEPROM) etc..Wherein, memory 110 is for storing program, the processor 120 after receiving and executing instruction,
Execute described program.
The processor 120 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor
120 can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit
(Network Processor, NP) etc..Can also be digital signal processor (DSP)), it is specific integrated circuit (ASIC), existing
Field programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware
Component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
It can be microprocessor or the processor be also possible to any conventional processor etc..
Network module 130 is used to establish the communication connection between electronic equipment 100 and external communications terminals by network,
Realize the transmitting-receiving operation of network signal and data.Above-mentioned network signal may include wireless signal or wire signal.
It is appreciated that structure shown in Figure 13 is only to illustrate, electronic equipment 100 may also include more than shown in Figure 13
Perhaps less component or with the configuration different from shown in Figure 13.Each component shown in Figure 13 can using hardware,
Software or combinations thereof is realized.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, appoints
What those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, answer
It is included within the scope of the present invention.
Claims (9)
1. a kind of pipe tobacco length determining method based on machine vision, which comprises the following steps:
Step 1, the camera image of tested pipe tobacco is obtained；
Step 2, the camera image of tested pipe tobacco is pre-processed, is converted to bianry image；
Step 3, the area of each connected region in the bianry image of tested pipe tobacco is calculated, and area is less than to the area threshold of setting
Connected region reject, Retention area be more than or equal to the area threshold connected region；
Step 4, the minimum circumscribed rectangle of the connected region retained is sought；
Step 5, the image length of tested pipe tobacco is sought according to minimum circumscribed rectangle, and according to the image length and reality of master sample
The image length of tested pipe tobacco is scaled physical length by the ratio data of border length.
2. the method according to claim 1, wherein in the step 2, comprising the following steps:
Judge the type of tested pipe tobacco, otherwise it is irregular pipe tobacco that definition, which is projected as the pipe tobacco of straight line as regular pipe tobacco,；
If tested pipe tobacco is regular pipe tobacco, the pixel that color is greater than the color threshold of setting is converted into 1, color is less than
Pixel equal to the color threshold is converted into 0, obtains the bianry image；
If tested pipe tobacco is irregular pipe tobacco, camera image is first subjected to Local standard deviation filtering processing, then create a corruption
Filtered image is carried out gradually corrosion treatment, then the image after corrosion treatment is not being changed by arbor object window
Become under conditions of the basic structure of image, all objects are all simplified to continuous lines, retain the elementary contour of image, most
Profile diagram is filled afterwards, the area pixel in lines is wholly converted into 0, the region outside lines is wholly converted into 1, obtains
To the bianry image.
3. the method according to claim 1, wherein calculating and being tested in the bianry image of pipe tobacco in the step 3
The area of each connected region, comprising:
A n dimension unit matrix is created, the connected region of bianry image is found according to unit matrix, and calculate each connected region
Area.
4. the method according to claim 1, wherein in the step 4, comprising:
The all pixels point for belonging to the same pixel connected region is distributed and is identically numbered, to belonging to different pixel connected regions
Different numbers is distributed in domain, according to the pixel of different number labels, calculates the external square of minimum of each pixel connected region
Shape.
5. according to the method described in claim 4, it is characterized in that, in the step 5,
If tested pipe tobacco is regular pipe tobacco, the length of minimum circumscribed rectangle is the image length of tested pipe tobacco；
If tested pipe tobacco is irregular pipe tobacco, the quantity m that pixel shared by pipe tobacco is tested in minimum circumscribed rectangle is sought, according to not
The data of the master sample of regular pipe tobacco calculate the corresponding physical length of each pixel, then the physical length y to be tested pipe tobacco
=x1+x2+x3+ ...+xm-2+xm-1+xm；
Wherein, y is the physical length of calculated tested pipe tobacco, and x is the corresponding physical length of each pixel；M is every quilt
Survey the quantity of pixel shared by pipe tobacco.
6. according to the method described in claim 4, it is characterized in that, the image length of the master sample and the ratio of physical length
The obtaining step of number of cases evidence, comprising:
To the master sample of known length, is handled according to the identical step of above-mentioned steps 1-4, obtain the minimum of master sample
After boundary rectangle, the image length of master sample is sought according to minimum circumscribed rectangle, establishes the image length and reality of master sample
The proportionate relationship of border length.
7. a kind of pipe tobacco length based on machine vision determines system, which is characterized in that comprise the following modules:
Image collection module, for obtaining the camera image of tested pipe tobacco；
Image conversion module is converted to bianry image for pre-processing the camera image of tested pipe tobacco；
Area calculation module, the area of each connected region in the bianry image for calculating tested pipe tobacco, and area is less than and is set
The connected region of fixed area threshold is rejected, and Retention area is more than or equal to the connected region of the area threshold；
Boundary rectangle seeks module, the minimum circumscribed rectangle of the connected region for seeking retaining；
Length computation module, for seeking the image length of tested pipe tobacco according to minimum circumscribed rectangle, and according to master sample
The image length of tested pipe tobacco is scaled physical length by the ratio data of image length and physical length.
8. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor perform claim requires the step of any one of 1-6 the method.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1-6 the method is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811109206.2A CN109215048B (en) | 2018-09-21 | 2018-09-21 | Tobacco shred length determining method and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811109206.2A CN109215048B (en) | 2018-09-21 | 2018-09-21 | Tobacco shred length determining method and system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109215048A true CN109215048A (en) | 2019-01-15 |
| CN109215048B CN109215048B (en) | 2021-05-07 |
Family
ID=64985103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811109206.2A Active CN109215048B (en) | 2018-09-21 | 2018-09-21 | Tobacco shred length determining method and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109215048B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889842A (en) * | 2019-11-28 | 2020-03-17 | 常德金鹏印务有限公司 | Method for detecting looseness of small cigarette pack cigarette label |
| CN111060014A (en) * | 2019-10-16 | 2020-04-24 | 杭州安脉盛智能技术有限公司 | Online self-adaptive tobacco shred width measuring method based on machine vision |
| CN112037195A (en) * | 2020-08-31 | 2020-12-04 | 中冶赛迪重庆信息技术有限公司 | Method, system, equipment and medium for detecting abnormal length of bar |
| CN113139951A (en) * | 2021-05-08 | 2021-07-20 | 上海烟草集团有限责任公司 | Method, system and equipment for characterizing attributes of tobacco lamina and computer readable storage medium |
| CN113838123A (en) * | 2021-08-16 | 2021-12-24 | 湖南磐钴传动科技有限公司 | Method for measuring tobacco shred morphology characteristics based on image processing |
| CN114529504A (en) * | 2021-12-27 | 2022-05-24 | 杭州安脉盛智能技术有限公司 | Online tobacco shred width measuring method integrating image segmentation and template matching |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6904917B2 (en) * | 2000-09-08 | 2005-06-14 | Japan Tobacco, Inc. | Method of manufacturing cigarette suppressing spread of burn and apparatus for manufacturing cigarette suppressing spread of burn |
| CN102679883A (en) * | 2012-05-09 | 2012-09-19 | 中国科学院光电技术研究所 | Tobacco shred width measuring method based on image processing |
| CN106052571A (en) * | 2016-07-21 | 2016-10-26 | 云南中烟工业有限责任公司 | Device and method for intelligent rapid detection of length and distribution of leaf silk for cigarette |
| CN106651872A (en) * | 2016-11-23 | 2017-05-10 | 北京理工大学 | Prewitt operator-based pavement crack recognition method and system |
-
2018
- 2018-09-21 CN CN201811109206.2A patent/CN109215048B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6904917B2 (en) * | 2000-09-08 | 2005-06-14 | Japan Tobacco, Inc. | Method of manufacturing cigarette suppressing spread of burn and apparatus for manufacturing cigarette suppressing spread of burn |
| CN102679883A (en) * | 2012-05-09 | 2012-09-19 | 中国科学院光电技术研究所 | Tobacco shred width measuring method based on image processing |
| CN106052571A (en) * | 2016-07-21 | 2016-10-26 | 云南中烟工业有限责任公司 | Device and method for intelligent rapid detection of length and distribution of leaf silk for cigarette |
| CN106651872A (en) * | 2016-11-23 | 2017-05-10 | 北京理工大学 | Prewitt operator-based pavement crack recognition method and system |
Non-Patent Citations (1)
| Title |
|---|
| 庄珍珍: "基于机器视觉的烟叶自动分级方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111060014A (en) * | 2019-10-16 | 2020-04-24 | 杭州安脉盛智能技术有限公司 | Online self-adaptive tobacco shred width measuring method based on machine vision |
| CN111060014B (en) * | 2019-10-16 | 2022-03-22 | 杭州安脉盛智能技术有限公司 | Online self-adaptive tobacco shred width measuring method based on machine vision |
| CN110889842A (en) * | 2019-11-28 | 2020-03-17 | 常德金鹏印务有限公司 | Method for detecting looseness of small cigarette pack cigarette label |
| CN110889842B (en) * | 2019-11-28 | 2023-08-22 | 常德金鹏印务有限公司 | Method for detecting loose degree of small box cigarette labels |
| CN112037195A (en) * | 2020-08-31 | 2020-12-04 | 中冶赛迪重庆信息技术有限公司 | Method, system, equipment and medium for detecting abnormal length of bar |
| CN112037195B (en) * | 2020-08-31 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Method, system, equipment and medium for detecting abnormal length of bar |
| CN113139951A (en) * | 2021-05-08 | 2021-07-20 | 上海烟草集团有限责任公司 | Method, system and equipment for characterizing attributes of tobacco lamina and computer readable storage medium |
| CN113838123A (en) * | 2021-08-16 | 2021-12-24 | 湖南磐钴传动科技有限公司 | Method for measuring tobacco shred morphology characteristics based on image processing |
| CN113838123B (en) * | 2021-08-16 | 2024-03-19 | 湖南磐钴传动科技有限公司 | Method for measuring appearance characteristics of cut tobacco based on image processing |
| CN114529504A (en) * | 2021-12-27 | 2022-05-24 | 杭州安脉盛智能技术有限公司 | Online tobacco shred width measuring method integrating image segmentation and template matching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109215048B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109215048A (en) | Pipe tobacco length determining method and system based on machine vision | |
| CN110287932B (en) | Road blocking information extraction method based on deep learning image semantic segmentation | |
| US8577611B2 (en) | System and method for analyzing trees in LiDAR data using views | |
| CN105427275B (en) | Crop field environment wheat head method of counting and device | |
| CN102982534B (en) | Canny edge detection dual threshold acquiring method based on chord line tangent method | |
| CN104820987B (en) | A kind of method based on optical imagery and microwave imagery detection target scattering performance deficiency | |
| EP2263191A1 (en) | System and method for identifying complex tokens in an image | |
| CN109886939A (en) | Bridge Crack detection method based on Tensor Voting | |
| CN112085675B (en) | Depth image denoising method, foreground segmentation method and human motion monitoring method | |
| CN116255912A (en) | Method and system for measuring static volume of package | |
| US8538695B2 (en) | System and method for analyzing trees in LiDAR data using views | |
| CN117635615B (en) | Defect detection method and system for realizing punching die based on deep learning | |
| CN106600616A (en) | Image background clutter measurement method and system | |
| CN108166362A (en) | A kind of automatic identifying method of asphalt pavement crack type | |
| CN105469384A (en) | Comprehensive evaluation methods of license plate image quality | |
| CN117274251B (en) | Tablet quality detection method in medicine production process based on image data | |
| CN116740579B (en) | Intelligent collection method for territorial space planning data | |
| CN113502721A (en) | Pavement performance determination method and system based on pavement texture | |
| CN111738310B (en) | Material classification method, device, electronic equipment and storage medium | |
| CN115311505A (en) | Silkworm cocoon classification method and purchase system based on cloud service big data platform | |
| CN107527365A (en) | A kind of method and device of dynamic calculation class circle object morphology diameter | |
| CN113192094A (en) | Ghost outline extraction method, electronic device and storage medium | |
| CN113469171A (en) | Method, device and medium for identifying interest area in SFR test card image | |
| CN115546621B (en) | Crop growth condition analysis method, device and application | |
| CN110059706B (en) | Detection method for single straight line in pepper-salt-rich noise environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |