CN109493335A - Piece type coefficient characterizing method, system, computer storage medium and the equipment of piece cigarette - Google Patents
Piece type coefficient characterizing method, system, computer storage medium and the equipment of piece cigarette Download PDFInfo
- Publication number
- CN109493335A CN109493335A CN201811346879.XA CN201811346879A CN109493335A CN 109493335 A CN109493335 A CN 109493335A CN 201811346879 A CN201811346879 A CN 201811346879A CN 109493335 A CN109493335 A CN 109493335A
- Authority
- CN
- China
- Prior art keywords
- cigarette
- value
- piece
- piece type
- connected region
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
-
- 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
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides the piece type coefficient characterizing method, system, computer storage medium and equipment of a kind of cigarette, and the piece type coefficient characterizing method of described cigarette includes: the original image for obtaining piece cigarette;Based on color intensity, the original image is split;Based on the image after segmentation, the circularity rate of piece cigarette is calculated, to characterize the piece type coefficient of piece cigarette by the circularity rate of described cigarette.The present invention explicitly uses machine vision image to characterize to the computation rule of the piece type coefficient of slice cigarette with circularity rate, the alignment degree that computation rule is the ratio of the area of minimum circumscribed circle in tobacco leaf area ratio to measure piece type;The appearance of circularity rate is so that beating and double roasting is all comparable in the piece type of different grade production, different technical parameters adjustment, different process section or even different roasting factories;For the personalized machined parameters according to piece type for finding each grade in time, adjustment feedback control beats leaf parameter and provides evaluation method and data supporting.
Description
Technical field
The invention belongs to tobacco leaf image process field, it is related to a kind of characterizing method and system, more particularly to a kind of cigarette
Piece type coefficient characterizing method, system, computer storage medium and equipment.
Background technique
The main measurement angle of the piece type of threshed redried strips be tobacco leaf circularity rate, intuitively from the point of view of just refer to beat
The form circle of the tobacco leaf of leaf redrying is non-round.Piece cigarette is round, and when chopping, no matter what angle tobacco leaf at that time is, cuts out
The Cut tobacco come is all more stable;Or not that the size of piece type is to the stabilization of Cut tobacco there is important influence, piece type air exercise
The technical arrangement plan of leaf redrying has great importance;Threshing redrying plant is relatively more to the concern of blade construction at this stage, than
It is few to the research of piece type coefficient compared with the size of concern blade;The method for judging piece smoked sheet type so far is sampled by people
Intuitively see whether piece cigarette is regular;To the rare report of research of piece smoked sheet type coefficient.
The prior art is to be compared according to the size of size of the external square of minimum of piece cigarette with the size of sieve pair
The size of piece cigarette is classified, it is intended to be carried out with the external square of the minimum of the area of tobacco leaf and the sieve of blade construction detection
Comparison, has not focused on the piece type coefficient of tobacco leaf, and the tobacco leaf in actual running environment into sieve is generally not exhibition
It opens, therefore the area of piece cigarette and whether is able to enter sieve there is also certain deviations.
Therefore, how the piece type coefficient characterizing method, system, computer storage medium and equipment of a kind of cigarette are provided, with
It solves the prior art and intuitively sees whether piece cigarette is regular by people's sampling, leading to the judgement regular to piece cigarette, there are errors etc. to lack
It falls into, has become those skilled in the art's technical problem urgently to be resolved in fact.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide the piece type coefficient of a kind of cigarette characterizations
Method, system, computer storage medium and equipment intuitively see whether piece cigarette advises by people's sampling for solving the prior art
It is whole, cause the judgement regular to piece cigarette to there are problems that error.
In order to achieve the above objects and other related objects, one aspect of the present invention provides the piece type coefficient characterization side of a kind of cigarette
Method, comprising: obtain the original image of piece cigarette;Based on color intensity, the original image is split;Based on the figure after segmentation
Picture calculates the circularity rate of piece cigarette, to characterize the piece type coefficient of piece cigarette by the circularity rate of described cigarette.
It is described to be based on color intensity in one embodiment of the invention, the step of original image is split packet
It includes: extracting R value, G value, the B value of rgb color space in original image;According to the R value, G value, B value of original image, calculate original
The gray matrix of image;The color intensity matrix of image is constructed by original image and gray matrix;According to for the color
The threshold value of the selected dedicated tunnel of intensity matrix carries out color segmentation to original image according to dedicated tunnel, forms binaryzation
Image;Tobacco leaf aperture potential in binary image is filled, the binary image after forming filling hole.
In one embodiment of the invention, the calculation formula of the gray matrix of original image are as follows: Gray=0.3*R+0.59*
G+0.11*B;Wherein, Gray indicates that gray matrix, R indicate the R value of rgb color space, and G indicates the G value of rgb color space, B
Indicate the B value of rgb color space;The constructive formula of color intensity matrix are as follows:Wherein, CI indicates color intensity square
Battle array.
In one embodiment of the invention, the basis is directed to the threshold of the selected dedicated tunnel of color intensity matrix
The step of being worth, carrying out color segmentation to original image according to dedicated tunnel, form binary image includes: by the color intensity
Pixel value in matrix is compared with the threshold value of dedicated tunnel, if the pixel value in the color intensity matrix is less than or equal to refer to
The threshold value of routing, then by 1 replacement of the pixel value;If the pixel value in the color intensity matrix is greater than the threshold of dedicated tunnel
Value, then by 0 replacement of the pixel value;By replacement pixel value, the binary image is formed.
In one embodiment of the invention, described to be filled to tobacco leaf aperture potential in binary image, formation is filled out
The step of binary image after filling hole includes: the connection for checking binary image;The position for the pixel that determination need to fill
Region;Default stuffing function is called to be filled the band of position that need to be filled, to form the binary image after filling hole.
In one embodiment of the invention, the image based on after segmentation calculates the circularity rate of described cigarette, to pass through
The step of piece type coefficient of the circularity rate characterization piece cigarette includes: to extract each company for the binary image after filling hole
The boundary curve in logical region, obtains the edge coordinate of the boundary curve;Find out the cross of the boundary curve of each connected region
Abscissa minimum value and abscissa maximum value in the distribution of coordinate and the ordinate in the distribution of ordinate are most
Small value and ordinate maximum value;With the vertical seat in abscissa minimum value and abscissa maximum value and the distribution of ordinate
The rectangle that minimum value and ordinate maximum value are formed is marked, binary image is divided into several matrix-blocks;The matrix-block
Quantity is identical as the quantity of connected region;The area of each connected region is calculated, and extracts the edge of each connected region, according to
Its edge coordinate generates corresponding minimum circumscribed circle;Calculate the area of the minimum circumscribed circle of each connected region;According to each company
The area in logical region and its area of corresponding minimum circumscribed circle, calculate the circularity rate of each connected region;Calculate each cigarette
Circularity rate calculate the circularity rate mean value of the batch piece cigarette and according to the circularity rate of each cigarette.
In one embodiment of the invention, binaryzation in the area of each connected region and each connected region counted
The point total number that data are 1 or 0;The area of the minimum circumscribed circle of each connected region is equal to pi constant multiplied by minimum external
Square of round radius;Wherein the radius of minimum circumscribed circle is the minimum value that discrimination formula is set up in default circle;The default circle
Whether interior discrimination formula is used to judge the boundary curve of each connected region in circle;The circularity rate of each connected region is equal to
The area of each connected region/its corresponding minimum circumscribed circle area.
Another aspect of the present invention provides the piece type coefficient characterization system of a kind of cigarette, comprising: module is obtained, for obtaining piece
The original image of cigarette;Divide module, for being based on color intensity, the original image is split;Computing module is used for base
Image after segmentation calculates the circularity rate of piece cigarette, to characterize the piece type coefficient of piece cigarette by the circularity rate of described cigarette.
Another aspect of the invention provides a kind of computer storage medium, is stored thereon with computer program, the computer journey
The piece type coefficient characterizing method of described cigarette is realized when sequence is executed by processor.
Last aspect of the present invention provides a kind of equipment, comprising: processor and memory;The memory is based on storing
Calculation machine program, the processor is used to execute the computer program of the memory storage, so that the equipment executes described
The piece type coefficient characterizing method of cigarette.
As described above, the piece type coefficient characterizing method of of the present invention cigarette, system, computer storage medium and setting
It is standby, it has the advantages that
The first, the present invention is for the first time explicitly with machine vision image to the computation rule of the piece type coefficient of slice cigarette, fortune
It is characterized with circularity rate, the regular journey that computation rule is the ratio of the area of minimum circumscribed circle in tobacco leaf area ratio to measure piece type
Degree;The appearance of circularity rate so that beating and double roasting different grade production, different technical parameters adjustment, different process section or even
The piece type of different roasting factories is all comparable;For the personalized machined parameters according to piece type for finding each grade in time, adjust
Whole feedback control beats leaf parameter and provides evaluation method and data supporting;
The second, since the composition inside cigarette finished product is mainly Cut tobacco, the fluctuation of cut tobacco be will affect in Cigarette
The stability of smoke behavior and physical index, and piece type is affected to cigarette leaves and tobacco structure, in order to guarantee finished cigarettes
The stability of flue gas and the stability of physical index need explicitly to be controlled to meet from piece type quality in cigarette and stablize
Demand.
Detailed description of the invention
Fig. 1 is shown as flow diagram of the piece type coefficient characterizing method of piece cigarette of the invention in an embodiment.
Fig. 2 is shown as the example schematic diagram of the original image of piece cigarette of the invention.
Fig. 3 is shown as the flow diagram of S12 in the piece type coefficient characterizing method of piece cigarette of the invention.
Fig. 4 is shown as the example schematic diagram of the color intensity matrix of piece cigarette of the invention.
Fig. 5 is shown as the example schematic diagram of tobacco leaf binaryzation matrix of the invention.
Fig. 6 is shown as the example schematic diagram of the binary image after filling hole of the invention.
Fig. 7 is shown as the flow diagram of S13 in the piece type coefficient characterizing method of piece cigarette of the invention.
Fig. 8 is shown as the example schematic diagram of the binary image of each connected region separation of the invention.
Fig. 9 is shown as the example schematic diagram of the boundary curve of each connected region of the invention.
Figure 10 is shown as the example schematic diagram of the minimum circumscribed circle of each connected region of the invention.
Figure 11 is shown as theory structure schematic diagram of the piece type coefficient characterization system of piece cigarette of the invention in an embodiment.
Component label instructions
The piece type coefficient of 11 cigarettes characterizes system
111 obtain module
112 segmentation modules
113 computing modules
S11~S13 step
S121~S125 step
S131~S137 step
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
The piece type coefficient characterizing method of of the present invention cigarette, system, the technical principle of computer storage medium and equipment
It is as follows:
The original image of tobacco leaf is obtained from the beating and double roasting image that industrial camera is shot, the color for calculating tobacco leaf image is strong
Degree is divided by the color intensity to image, obtains the binaryzation matrix of tobacco leaf image, carries out respectively to the location information of tobacco leaf
Separation forms the binaryzation matrix of each independent cigarette image, solves the central point and area of separation tobacco leaf image.It mentions
The boundary curve for taking image, to coordinate fitting minimum circumscribed circle equation, the radius for obtaining minimum circumscribed circle, face of boundary curve
Product;The calculation for further constructing the circularity rate of the separation tobacco leaf image is the ratio of minimum circumscribed circle in tobacco leaf area ratio,
To characterize the piece type coefficient of piece leaf.
Embodiment one
The present embodiment provides the piece type coefficient characterizing methods of a kind of cigarette, comprising:
Obtain the original image of piece cigarette;
Based on color intensity, the original image is split;
Based on the image after segmentation, the circularity rate of piece cigarette is calculated, to characterize the piece of piece cigarette by the circularity rate of described cigarette
Type coefficient.
The piece type coefficient characterizing method of piece cigarette provided by the present embodiment is described in detail below with reference to diagram.Please
Refering to fig. 1, flow diagram of the piece type coefficient characterizing method of display sheet cigarette in an embodiment.As shown in Figure 1, described cigarette
Piece type coefficient characterizing method specifically include following steps:
S11 obtains the original image of piece cigarette.In the present embodiment, tobacco leaf of the beating and double roasting before roasting is sampled to form piece cigarette,
Being placed under image capture device for separation acquires original image, and the original image of piece cigarette is obtained from described image acquisition equipment, is asked
Referring to Fig.2, being shown as the example schematic diagram of the original image of piece cigarette.
S12 is based on color intensity, is split to the original image.In the present embodiment, the color intensity energy of image
It is enough effectively to solve the image conditions segmentation research that background is uneven, colour gamut has intersection.Therefore, image is carried out with color intensity
Segmentation.Referring to Fig. 3, being shown as the flow diagram of S12.As shown in figure 3, the S12 the following steps are included:
S121 extracts R value, G value, the B value of rgb color space in original image.
That is, the R value of rgb color space is expressed as R=RGB (::, 1), the G value of rgb color space is expressed as G=RGB
(::, 2), the B value of rgb color space are expressed as B=RGB (::, 3).
S122 calculates the gray matrix of original image according to the R value, G value, B value of original image.
In the present embodiment, shown in the calculation formula of the gray matrix of original image such as formula (1):
Gray=0.3*R+0.59*G+0.11*B formula (1)
Wherein, Gray indicates that gray matrix, R indicate the R value of rgb color space, and G indicates the G value of rgb color space, and B is indicated
The B value of rgb color space.
S123 constructs the color intensity matrix of image by original image and gray matrix.Referring to Fig. 4, being shown as piece
The example schematic diagram of the color intensity matrix of cigarette.
In the present embodiment, shown in the constructive formula of color intensity matrix such as formula (2):
Wherein, CI indicates color intensity matrix.
S124, according to the threshold value for being directed to the selected dedicated tunnel of color intensity matrix, according to dedicated tunnel to original
Beginning image carries out color segmentation, forms binary image.
Specifically, the pixel value in the color intensity matrix is compared with the threshold value of dedicated tunnel, if the face
Pixel value in intensity of colour matrix is less than or equal to the threshold value of dedicated tunnel, then by 1 replacement of the pixel value;If the color intensity
Pixel value in matrix is greater than the threshold value of dedicated tunnel, then by 0 replacement of the pixel value;By replacement pixel value, described in formation
Binary image BW.S124 can be with representation formula (3):
Wherein, 1≤i≤m, 1≤j≤n, m are the line number of Matrix C I, and n is the columns of CI.
For example, according to for the threshold value 0.95 for specifying 3 channels selected by color intensity Matrix C I, according to specified 3 channels into
Row color segmentation forms tobacco leaf binaryzation matrix B W as shown in Figure 5, and 0 corresponds to black region, and 1 corresponds to white area.
S125 is filled tobacco leaf aperture potential in binary image, the binary image after forming filling hole.
Specifically, the S125 includes the connection for checking binary image;The band of position for the pixel that determination need to fill;
Default stuffing function is called to be filled the band of position that need to be filled, to form the binary image BW1 after filling hole.Example
Such as, the binary image after hole is filled as shown in Figure 6.
S13 calculates the circularity rate of piece cigarette based on the image after segmentation, to characterize piece cigarette by the circularity rate of described cigarette
Piece type coefficient.Referring to Fig. 7, being shown as the flow diagram of S13.As shown in fig. 7, the S13 specifically includes the following steps:
S131 extracts the boundary curve of each connected region, obtains the side for the binary image after filling hole
The edge coordinate of edge curve.Black region as shown in FIG. 6 is connected region.
S132 finds out the abscissa minimum value in the distribution of the abscissa of the boundary curve of each connected region
Ordinate minimum value Ymin and ordinate maximum value in the distribution of Xmin and abscissa maximum value Xmax and ordinate
Ymax。
S133, it is minimum with the ordinate in abscissa minimum value and abscissa maximum value and the distribution of ordinate
Binary image, is divided into several matrix-blocks by the rectangle that value and ordinate maximum value are formed;The quantity of the matrix-block with
The quantity of connected region is identical.
For example, the rectangle formed with the coordinate of aforementioned four angle point, is divided into binary image BW1 as shown in Figure 6
33 fritters, there are the binaryzation matrixes of corresponding independent 1 tobacco leaf for each fritter the inside;Setting BW2_k indicates in BW1
The tobacco leaf binaryzation matrix that k-th of independent connected region is split, for example, each connected region separation as shown in Figure 8
Binary image, wherein binaryzation data are that the region of 1 composition indicates connected region.
S134, calculates the area of each connected region, and extracts the edge of each connected region, according to its edge coordinate,
Generate corresponding minimum circumscribed circle.
Specifically, the calculation of the elemental area SArea of each connected region BW2_k is binaryzation in statistics BW2_k
The point total number that data are 1.
Specifically, it extracts the edge of BW2_k binaryzation connected region image and calculates its corresponding edge coordinate Xs, Ys;
Xs is calculated, the average value of Ys, by Xs, the average value of Ys is set as center of circle mxs, and the half of mys and corresponding minimum circumscribed circle
R is arranged in the radius of diameter, minimum circumscribed circlew.Wherein, the boundary curve of each connected region is as shown in figure 9, each connected region
Minimum circumscribed circle is as shown in Figure 10.The radius of minimum circumscribed circle is the minimum value that discrimination formula is set up in default circle;It is described default
The boundary curve that discrimination formula is used to judge each connected region in circle presets discrimination formula such as formula in circle whether in circle
(4) shown in:
That is, judging that the edge of connected region BW2_k is bent by discrimination formula in default circle during drawing circle
Whether line is all in circle.
S135 calculates the area of the minimum circumscribed circle of each connected region.In the present embodiment, each connected region BW2_
The area of k minimum circumscribed circle indicates that the calculation formula of Darea such as formula (5) is as follows with Darea:
Wherein, pi is pi constant.
S136 calculates each connected region according to the area of each connected region and its area of corresponding minimum circumscribed circle
The circularity rate in domain.
Specifically, the circularity rate of each connected region is equal to area/its corresponding minimum circumscribed circle of each connected region
Area.The calculation formula of the circularity rate of connected region is as follows:
Wherein, YDL indicates the circularity rate of connected region, and SArea indicates that the area of each connected region, Darea indicate every
The area of the corresponding minimum circumscribed circle of a connected region.
S137 calculates the circularity rate of each cigarette, and according to the circularity rate of each cigarette, calculates the circularity of the batch piece cigarette
Rate mean value.
The piece type coefficient characterizing method of sheet above cigarette is applied in following embodiment:
It often will appear the tobacco leaf of no complete chopping in the link of cigarette chopping, be commonly called as so-called " petal pipe tobacco ", flower
The characteristic feature of leaflet silk is exactly that compare cut tobacco wide and justify;Utilize the circularity that piece type is characterized in the piece type coefficient characterizing method of piece cigarette
The mode of rate identifies normal cut tobacco and petal cut tobacco;10 cut tobaccos in total are shot according to each, wherein the quantity of petal cigarette
It successively from 0:10, is put into cut tobacco and takes pictures, identify petal cigarette with the circularity rate difference of petal cigarette and normal cut tobacco
Quantity.From piece type coefficient, the circularity rate of petal cigarette is more than or equal to 0.2;The circularity rate of normal cut tobacco is less than 0.2;
Normal cut tobacco is identified with 0.2 threshold value, and the results are shown in Table 1 with petal cut tobacco.
Table 1: with the result of circularity rate identification petal tobacco leaf
The present embodiment also provides a kind of computer storage medium (also known as computer readable storage medium), is stored thereon with
Computer program realizes the piece type coefficient characterizing method of power sheet above cigarette when the computer program is executed by processor.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of computer program is crossed to complete.Computer program above-mentioned can store in a computer readable storage medium
In.When being executed, execution includes the steps that above-mentioned each method embodiment to the program;And storage medium above-mentioned include: ROM,
The various media that can store program code such as RAM, magnetic or disk.
The piece type coefficient characterizing method of piece cigarette described in the present embodiment, has the advantages that
The first, the present invention is for the first time explicitly with machine vision image to the computation rule of the piece type coefficient of slice cigarette, fortune
It is characterized with circularity rate, the regular journey that computation rule is the ratio of the area of minimum circumscribed circle in tobacco leaf area ratio to measure piece type
Degree;The appearance of circularity rate so that beating and double roasting different grade production, different technical parameters adjustment, different process section or even
The piece type of different roasting factories is all comparable;For the personalized machined parameters according to piece type for finding each grade in time, adjust
Whole feedback control beats leaf parameter and provides evaluation method and data supporting;
The second, since the composition inside cigarette finished product is mainly Cut tobacco, the fluctuation of cut tobacco be will affect in Cigarette
The stability of smoke behavior and physical index, and piece type is affected to cigarette leaves and tobacco structure, in order to guarantee finished cigarettes
The stability of flue gas and the stability of physical index need explicitly to be controlled to meet from piece type quality in cigarette and stablize
Demand.
Embodiment two
The present embodiment provides the piece type coefficients of a kind of cigarette to characterize system, comprising:
Module is obtained, for obtaining the original image of piece cigarette;
Divide module, for being based on color intensity, the original image is split;
Computing module, for the circularity rate of piece cigarette being calculated, to pass through the circularity rate of described cigarette based on the image after segmentation
Characterize the piece type coefficient of piece cigarette.
It is described in detail below with reference to piece type coefficient characterization system of the diagram to piece cigarette provided by the present embodiment.It needs
To illustrate that, it should be understood that following table levies the division for dividing a kind of only logic function of the modules of system, practical real
It can completely or partially be integrated on a physical entity now, it can also be physically separate.And these modules can all with
Software is realized by way of processing element calls, and can also all be realized, can be passed through with part of module in the form of hardware
Processing element calls the form of software to realize that part of module passes through formal implementation of hardware.Such as: x module can be individually to set
Vertical processing element also can integrate and realize in some chip of following characterization systems.In addition, x module can also be with journey
The form of sequence code is stored in the memory of following characterization systems, is called simultaneously by some processing element of following characterization systems
Execute the function of following x module.The realization of other modules is similar therewith.These modules completely or partially can integrate together,
It can also independently realize.Processing element described here can be a kind of integrated circuit, the processing capacity with signal.It is realizing
In the process, each step of the above method or the above modules can pass through the integrated logic circuit of the hardware in processor elements
Or the instruction of software form is completed.The one or more that these modules can be arranged to implement above method below integrates
Circuit, such as: one or more specific integrated circuit (Application Specific Integrated Circuit, abbreviations
ASIC), one or more microprocessors (Digital Singnal Processor, abbreviation DSP), one or more scene
Programmable gate array (Field Programmable Gate Array, abbreviation FPGA) etc..When some following module passes through processing
When the form of element scheduler program code is realized, which can be general processor, such as central processing unit (Central
Processing Unit, abbreviation CPU) or it is other can be with the processor of caller code.These modules can integrate one
It rises, is realized in the form of system on chip (System-on-a-chip, abbreviation SOC).
Figure 11 is please referred to, theory structure schematic diagram of the piece type coefficient characterization system of piece cigarette in an embodiment is shown as.
As shown in figure 11, the piece type coefficient characterization system 11 of described cigarette includes: to obtain module 111, segmentation module 112 and computing module
113。
The original image for obtaining module 111 and being used to obtain piece cigarette.In the present embodiment, the cigarette beating and double roasting before roasting
Leaf samples to form piece cigarette, and being placed under image capture device for separation acquires original image, obtains piece from described image acquisition equipment
The original image of cigarette.
The segmentation module 112 coupled with the acquisition module 111 is used to carry out the original image based on color intensity
Segmentation.In the present embodiment, the color intensity of image can effectively solve the problem that the image conditions point that background is uneven, colour gamut has intersection
Cut research.Therefore, image is split with color intensity.
The segmentation module 112 is specifically used for extracting R value, G value, the B value of rgb color space in original image;According to original
R value, G value, the B value of beginning image, calculate the gray matrix of original image;The face of image is constructed by original image and gray matrix
Intensity of colour matrix;According to the threshold value for being directed to the selected dedicated tunnel of color intensity matrix, according to dedicated tunnel to original
Image carries out color segmentation, forms binary image;Tobacco leaf aperture potential in binary image is filled, filling is formed
Binary image after hole.
The computing module 113 coupled with the segmentation module 112 is used to calculate the circularity of piece cigarette based on the image after segmentation
Rate, to characterize the piece type coefficient of piece cigarette by the circularity rate of described cigarette.
The computing module 113 is specifically used for extracting each connected region for the binary image after filling hole
Boundary curve obtains the edge coordinate of the boundary curve;Find out point of the abscissa of the boundary curve of each connected region
Ordinate in the distribution of abscissa minimum value Xmin and abscissa maximum value Xmax and ordinate in cloth range is most
Small value Ymin and ordinate maximum value Ymax.With the distribution of abscissa minimum value and abscissa maximum value and ordinate
In ordinate minimum value and ordinate maximum value formed rectangle, binary image is divided into several matrix-blocks;It calculates
The area of each connected region, and the edge of each connected region is extracted, according to its edge coordinate, it is external to generate corresponding minimum
Circle;Calculate the area of the minimum circumscribed circle of each connected region;It is outer according to the area of each connected region and its corresponding minimum
Round area is connect, the circularity rate of each connected region is calculated;The circularity rate of each cigarette is calculated, and according to the circularity of each cigarette
Rate calculates the circularity rate mean value of the batch piece cigarette.
Specifically, it is every to calculate to be used to count the point total number that binaryzation data are 1 in BW2_k for the computing module 113
The elemental area of a connected region BW2_k;It extracts the edge of BW2_k binaryzation connected region image and calculates its corresponding edge
Coordinate Xs, Ys;Xs is calculated, the average value of Ys, by Xs, the average value of Ys is set as center of circle mxs, and mys and corresponding minimum are outer
Connect round radius.The radius of minimum circumscribed circle is the minimum value that discrimination formula is set up in default circle;Differentiate in the default circle public
Formula is used to judge the boundary curve of each connected region whether in circle, i.e., during drawing circle, by sentencing in default circle
Whether other formula judges the boundary curve of connected region BW2_k all in circle.The circularity rate of each connected region is equal to each company
Area/its corresponding minimum circumscribed circle area in logical region.
Embodiment three
The present embodiment provides a kind of equipment, the equipment include: processor, memory, transceiver, communication interface or/and
System bus;Memory and communication interface pass through system bus and mutual communication are connect and completed with processor and transceiver,
Memory is for storing computer program, and communication interface is used for and other equipment are communicated, and processor and transceiver are for transporting
Row computer program makes equipment execute each step of the piece type coefficient characterizing method of piece cigarette as above.
System bus mentioned above can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, abbreviation PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, abbreviation EISA) bus etc..The system bus can be divided into address bus, data/address bus, control bus etc..
Communication interface is for realizing the communication between database access device and other equipment (such as client, read-write library and read-only library).
Memory may include random access memory (Random Access Memory, abbreviation RAM), it is also possible to further include non-volatile
Property memory (non-volatile memory), for example, at least a magnetic disk storage.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
Abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.;It can also be digital signal processor
(Digital Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific
Integrated Circuit, abbreviation ASIC), field programmable gate array (Field Programmable Gate Array,
Abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.
The protection scope of the piece type coefficient characterizing method of of the present invention cigarette is not limited to the present embodiment the step of enumerating
Execute sequence, increase and decrease, step replace realized scheme all the step of the prior art that all principles according to the present invention are done
Including within the scope of the present invention.
System is characterized the present invention also provides the piece type coefficient of a kind of cigarette, and the piece type coefficient characterization system of described cigarette can be with
Realize the piece type coefficient characterizing method of of the present invention cigarette, but the piece type coefficient characterizing method of of the present invention cigarette
Realization device include but is not limited to the piece cigarette that the present embodiment is enumerated piece type coefficient characterization system structure, it is all according to the present invention
The principle malformation and replacement of the prior art done, be included in protection scope of the present invention.
In conclusion piece type coefficient characterizing method, system, computer storage medium and the equipment of of the present invention cigarette,
It has the advantages that
The first, the present invention is for the first time explicitly with machine vision image to the computation rule of the piece type coefficient of slice cigarette, fortune
It is characterized with circularity rate, the regular journey that computation rule is the ratio of the area of minimum circumscribed circle in tobacco leaf area ratio to measure piece type
Degree;The appearance of circularity rate so that beating and double roasting different grade production, different technical parameters adjustment, different process section or even
The piece type of different roasting factories is all comparable;For the personalized machined parameters according to piece type for finding each grade in time, adjust
Whole feedback control beats leaf parameter and provides evaluation method and data supporting;
The second, since the composition inside cigarette finished product is mainly Cut tobacco, the fluctuation of cut tobacco be will affect in Cigarette
The stability of smoke behavior and physical index, and piece type is affected to cigarette leaves and tobacco structure, in order to guarantee finished cigarettes
The stability of flue gas and the stability of physical index need explicitly to be controlled to meet from piece type quality in cigarette and stablize
Demand.
The present invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (10)
1. the piece type coefficient characterizing method of a kind of cigarette characterized by comprising
Obtain the original image of piece cigarette;
Based on color intensity, the original image is split;
Based on the image after segmentation, the circularity rate of piece cigarette is calculated, to characterize the piece type system of piece cigarette by the circularity rate of described cigarette
Number.
2. the piece type coefficient characterizing method of according to claim 1 cigarette, which is characterized in that it is described to be based on color intensity,
The step of being split to the original image include:
Extract R value, G value, the B value of rgb color space in original image;
According to the R value, G value, B value of original image, the gray matrix of original image is calculated;
The color intensity matrix of image is constructed by original image and gray matrix;
According to the threshold value for being directed to the selected dedicated tunnel of color intensity matrix, original image is carried out according to dedicated tunnel
Color segmentation forms binary image;
Tobacco leaf aperture potential in binary image is filled, the binary image after forming filling hole.
3. the piece type coefficient characterizing method of according to claim 2 cigarette, which is characterized in that
The calculation formula of the gray matrix of original image are as follows:
Gray=0.3*R+0.59*G+0.11*B;
Wherein, Gray indicates that gray matrix, R indicate the R value of rgb color space, and G indicates the G value of rgb color space, and B is indicated
The B value of rgb color space;
The constructive formula of color intensity matrix are as follows:
Wherein, CI indicates color intensity matrix.
4. the piece type coefficient characterizing method of according to claim 3 cigarette, which is characterized in that
The basis is directed to the threshold value of the selected dedicated tunnel of color intensity matrix, according to dedicated tunnel to original image
Carry out color segmentation, formed binary image the step of include:
Pixel value in the color intensity matrix is compared with the threshold value of dedicated tunnel, if in the color intensity matrix
Pixel value be less than or equal to dedicated tunnel threshold value, then by the pixel value with 1 replace;If the pixel in the color intensity matrix
Value is greater than the threshold value of dedicated tunnel, then by 0 replacement of the pixel value;By replacement pixel value, the binary image is formed.
5. the piece type coefficient characterizing method of according to claim 3 cigarette, which is characterized in that described in binary image
The step of potential tobacco leaf aperture is filled, binary image after forming filling hole include:
Check the connection of binary image;
The band of position for the pixel that determination need to fill;
Default stuffing function is called to be filled the band of position that need to be filled, to form the binary image after filling hole.
6. the piece type coefficient characterizing method of according to claim 5 cigarette, which is characterized in that the figure based on after segmentation
Picture calculates the circularity rate of described cigarette, to include: by the step of piece type coefficient of circularity rate characterization piece cigarette
For the binary image after filling hole, the boundary curve of each connected region is extracted, the boundary curve is obtained
Edge coordinate;
Find out abscissa minimum value in the distribution of the abscissa of the boundary curve of each connected region and abscissa most
Ordinate minimum value and ordinate maximum value in big value and the distribution of ordinate;
With the ordinate minimum value in abscissa minimum value and abscissa maximum value and the distribution of ordinate and indulge seat
The rectangle that maximum value is formed is marked, binary image is divided into several matrix-blocks;The quantity and connected region of the matrix-block
Quantity it is identical;
The area of each connected region is calculated, and extracts the edge of each connected region, according to its edge coordinate, is generated corresponding
Minimum circumscribed circle;
Calculate the area of the minimum circumscribed circle of each connected region;
According to the area of each connected region and its area of corresponding minimum circumscribed circle, the circularity of each connected region is calculated
Rate;
The circularity rate of each cigarette is calculated, and according to the circularity rate according to each cigarette, the circularity rate for calculating the batch piece cigarette is equal
Value.
7. the piece type coefficient characterizing method of according to claim 6 cigarette, which is characterized in that
The point total number that binaryzation data are 1 or 0 in the area of each connected region and each connected region counted;
The area of the minimum circumscribed circle of each connected region is equal to pi constant multiplied by square of the radius of minimum circumscribed circle;Its
The radius of middle minimum circumscribed circle is the minimum value that discrimination formula is set up in default circle;Discrimination formula is for judging in the default circle
Whether the boundary curve of each connected region is in circle;
The circularity rate of each connected region is equal to area/its corresponding minimum circumscribed circle area of each connected region.
8. the piece type coefficient of a kind of cigarette characterizes system characterized by comprising
Module is obtained, for obtaining the original image of piece cigarette;
Divide module, for being based on color intensity, the original image is split;
Computing module, for calculating the circularity rate of piece cigarette based on the image after segmentation, to be characterized by the circularity rate of described cigarette
The piece type coefficient of piece cigarette.
9. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is by processor
The piece type coefficient characterizing method of piece cigarette described in any one of claims 1 to 7 is realized when execution.
10. a kind of equipment characterized by comprising processor and memory;
The memory is used to execute the computer journey of the memory storage for storing computer program, the processor
Sequence, so that the equipment executes the piece type coefficient characterizing method of the piece cigarette as described in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811346879.XA CN109493335A (en) | 2018-11-13 | 2018-11-13 | Piece type coefficient characterizing method, system, computer storage medium and the equipment of piece cigarette |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811346879.XA CN109493335A (en) | 2018-11-13 | 2018-11-13 | Piece type coefficient characterizing method, system, computer storage medium and the equipment of piece cigarette |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109493335A true CN109493335A (en) | 2019-03-19 |
Family
ID=65694272
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811346879.XA Pending CN109493335A (en) | 2018-11-13 | 2018-11-13 | Piece type coefficient characterizing method, system, computer storage medium and the equipment of piece cigarette |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493335A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110889839A (en) * | 2019-11-27 | 2020-03-17 | 贵州中烟工业有限责任公司 | Characterization method and system for threshing and redrying tobacco flake |
CN112330587A (en) * | 2020-07-01 | 2021-02-05 | 河北工业大学 | Silver wire type contact ablation area identification method based on edge detection |
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 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201488706U (en) * | 2009-09-02 | 2010-05-26 | 中国科学院沈阳科学仪器研制中心有限公司 | Index detection device of cigarette or filter rod |
CN103177256A (en) * | 2013-04-02 | 2013-06-26 | 上海理工大学 | Method for identifying display state of traffic signal lamp |
CN103808263A (en) * | 2014-01-20 | 2014-05-21 | 北京派得伟业科技发展有限公司 | High-throughput detection method for grain form parameters |
EP2881000A1 (en) * | 2012-07-31 | 2015-06-10 | Japan Tobacco Inc. | Sheet tobacco weight measurement device, measurement method thereof, sheet tobacco manufacturing system and manufacturing method thereof |
CN105303184A (en) * | 2015-11-25 | 2016-02-03 | 中国矿业大学(北京) | Method for accurately identifying ground features in satellite remote-sensing image |
CN108776978A (en) * | 2018-05-28 | 2018-11-09 | 江苏中烟工业有限责任公司 | A kind of threshed redried strips piece shape characterizing method |
-
2018
- 2018-11-13 CN CN201811346879.XA patent/CN109493335A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201488706U (en) * | 2009-09-02 | 2010-05-26 | 中国科学院沈阳科学仪器研制中心有限公司 | Index detection device of cigarette or filter rod |
EP2881000A1 (en) * | 2012-07-31 | 2015-06-10 | Japan Tobacco Inc. | Sheet tobacco weight measurement device, measurement method thereof, sheet tobacco manufacturing system and manufacturing method thereof |
CN103177256A (en) * | 2013-04-02 | 2013-06-26 | 上海理工大学 | Method for identifying display state of traffic signal lamp |
CN103808263A (en) * | 2014-01-20 | 2014-05-21 | 北京派得伟业科技发展有限公司 | High-throughput detection method for grain form parameters |
CN105303184A (en) * | 2015-11-25 | 2016-02-03 | 中国矿业大学(北京) | Method for accurately identifying ground features in satellite remote-sensing image |
CN108776978A (en) * | 2018-05-28 | 2018-11-09 | 江苏中烟工业有限责任公司 | A kind of threshed redried strips piece shape characterizing method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110889839A (en) * | 2019-11-27 | 2020-03-17 | 贵州中烟工业有限责任公司 | Characterization method and system for threshing and redrying tobacco flake |
CN110889839B (en) * | 2019-11-27 | 2022-11-25 | 贵州中烟工业有限责任公司 | Characterization method and system for threshing and redrying tobacco flake |
CN112330587A (en) * | 2020-07-01 | 2021-02-05 | 河北工业大学 | Silver wire type contact ablation area identification method based on edge detection |
CN112330587B (en) * | 2020-07-01 | 2022-05-20 | 河北工业大学 | Silver wire type contact ablation area identification method based on edge detection |
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 |
CN113139951B (en) * | 2021-05-08 | 2022-11-22 | 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 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109493335A (en) | Piece type coefficient characterizing method, system, computer storage medium and the equipment of piece cigarette | |
Zhang et al. | Growth monitoring of greenhouse lettuce based on a convolutional neural network | |
US9008409B2 (en) | Method and system for digital image analysis of ear traits | |
CN105229697B (en) | Multi-modal prospect background segmentation | |
CN110163810A (en) | A kind of image processing method, device and terminal | |
US8548257B2 (en) | Distinguishing between faces and non-faces | |
CN104856680A (en) | Automatic detection method and system for neonatal jaundice | |
CN109740721B (en) | Wheat ear counting method and device | |
US10620175B2 (en) | Apparatus and processes for photosynthetic activity measurement and mapping | |
CN108109145A (en) | Picture quality detection method, device, storage medium and electronic device | |
CN112974303B (en) | Hyperspectrum-based fruit quality detection method, device and medium | |
CN113808153A (en) | Tomato maturity detection method and device, computer equipment and storage medium | |
CN109101891A (en) | A kind of rice pest detection system and its detection method merging artificial intelligence | |
CN106530361A (en) | Color correction method for color face image | |
WO2019152499A1 (en) | Systems and methods for image signal processor tuning using a reference image | |
WO2019152534A1 (en) | Systems and methods for image signal processor tuning | |
DE202014010866U1 (en) | Specifiability of images | |
CN109903265A (en) | A kind of image change area detecting threshold value setting method, system and its electronic device | |
CN113033401A (en) | Human activity change recognition and supervision method for ecological protection red line | |
US9754155B2 (en) | Method and system for generating intrinsic images using a single reflectance technique | |
CN111951196A (en) | Progressive point cloud down-sampling method and device based on graph | |
CN115545383A (en) | Binocular stereoscopic vision detection method for crisp appearance quality of strawberries | |
CN101631259A (en) | Method for evaluating color fidelity and subsystem thereof | |
CN112000761A (en) | Data analysis method and device, electronic equipment and computer readable storage medium | |
CN115880429A (en) | Method and system for determining vegetable strong seedling judgment model |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |