CN106503681A - A kind of digital picture stage division of wool scale layer - Google Patents
A kind of digital picture stage division of wool scale layer Download PDFInfo
- Publication number
- CN106503681A CN106503681A CN201610966643.0A CN201610966643A CN106503681A CN 106503681 A CN106503681 A CN 106503681A CN 201610966643 A CN201610966643 A CN 201610966643A CN 106503681 A CN106503681 A CN 106503681A
- Authority
- CN
- China
- Prior art keywords
- wool
- digital picture
- peak point
- scale layer
- image
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The present invention relates to a kind of digital picture stage division of wool scale layer, comprises the following steps:Denoising is carried out to the digital picture for getting;Digital picture after by denoising carries out binaryzation;Digital picture after to binaryzation carries out the straight-line detection at Pilus Caprae seu Oviss edge, and chooses suitable region;Wool fiber in the appropriate area of selection is projected to the waveform for obtaining reacting wool scale present position in horizontal direction;The first derivative and second dervative of calculated wavy curve, the value according to first derivative and second dervative determine peak point;The spacing of adjacent peak point is calculated, the spacing according to adjacent peak point is classified.The present invention quickly equitably can be evaluated to wool modifying effect.
Description
Technical field
The present invention relates to wool scale layer classification technique field, more particularly to a kind of digital picture of wool scale layer point
Level method.
Background technology
Pilus Caprae seu Oviss are a kind of natural high quality protein fibers, are one of important raw and processed materials of modern textile industry.Pilus Caprae seu Oviss have
Many excellent characteristics, for example, as warmth retention property is good, the strong good, hygroscopicity of elasticity, soft touch, be not easy dirty etc..These property
The fabric of Pilus Caprae seu Oviss can be caused to have the advantage of oneself, with the various senior fabric for clothes of the Pilus Caprae seu Oviss system of can knitting:Such as cassimere, there is feel
Glutinous, the elastic good, quality of cunning is abundant, the medicated clothing of the natural season in spring and autumn of gloss;Such as medium weight fancy suiting, textured abundant, warmth retention property is strong,
The winter clothing of comfortable feel.Woollen sweater that such as winter often wears etc..The industrial woollen goods of the Pilus Caprae seu Oviss system of can also knitting, woollen blanket, liner
Etc. important materials.
But Pilus Caprae seu Oviss are also not perfect, it also has some shortcomings.As wool fabric is using washing of drum type washing machine
When be easy to so that fabric size occur significant change, this be due to direction friction effect be easy to occur felting deformation;Secondly,
The presence of wool scale layer causes wool fabric there is prodding and itching feeling when wearing next to the skin, and this can largely effect on wearing for wool fabric
Experience, so as to limit its purposes;Meanwhile, wool product needs are can be only achieved under higher temperature compared with other materials
Color, which results in a large amount of costs on the energy in dyeing process;Additionally, wool product need to pass through softness in Final finishing
The last phase tidying up process such as change, antibacterial, scale layer cause these auxiliary agents to reduce the absorbability of wool fabric so that Final finishing becomes
Increasingly difficult.
With the more and more higher that the progress in epoch, requirement of the people to wool fabric performance also become.People are not only intended merely to
The warming effect that Pilus Caprae seu Oviss dress ornament can have in winter, also requires that Pilus Caprae seu Oviss dress ornament being capable of fashion, easy cleaning, comfortable and easy to wear, price parent
People etc..This just to the dyeability of wool fabric, anti-felting performance, permeability, wear when sensation etc. propose very high
Requirement.Simultaneously as the reinforcement of social environment consciousness, people more pay attention to for environment.Textile dyeing and finishing industry is due to right
Environment is easy to produce impact, environmental protection of should more doing everything possible.For the Pilus Caprae seu Oviss for having many good characteristics, people
Wish also go on clean environment firendly, the new approach of low energy to the dyeing and finishing processing of this excellent natural fiber.Therefore, using right
Eco-friendly method is modified to Pilus Caprae seu Oviss, is eliminated the negative effect that scale layer is caused, is an imperative research.
Why Pilus Caprae seu Oviss have above-mentioned many characteristics, and there are special morphosiss mainly due to it.Wherein wool fiber
The Microstructure of epidermal scale on surface, has very big impact to the process based prediction model of wool fabric.These laminar cells are just
Covering is overlapped as the scale that reptile body surface is covered, the outside of hair shaft is coated on.Root is attached to hair shaft, and taper stretches out
Hair shaft surface and tippy tea is pointed to, by protruding from fiber surface in various degree and being flared out, form a stepped knot in steep face
Structure.
Scale layer is one of distinctive structure of wool fiber, and it is susceptible to when being and result in woolen dyed difficult, washing
The reason for prodding and itching feeling of felting deformation and dress.Scale layer is glued by cell membrane complexes by cornified flat cell
Connect and form.The squamous cell of Pilus Caprae seu Oviss is made up of three parts:Respectively epicuticula, scale outer layer and scale internal layer.
It is not good that the Microstructure of epidermal scale of wool surface causes the dress of wool fabric to experience, and also adds to the dyeing and finishing in production
Work process brings a lot of troubles.Therefore, Pilus Caprae seu Oviss are carried out with the modified research of stripping squama just to arise at the historic moment.Grinding for squama is shelled with regard to Pilus Caprae seu Oviss
Studying carefully has had considerably long history, is initially the shrinkproof performance in order to improve wool fabric, improves the dimensional stability of product,
Woolen is made to obtain the performance of " machine washable ".With people to the structure of scale layer and it Pilus Caprae seu Oviss processing take during not
The understanding of same-action is more deep, the research that Pilus Caprae seu Oviss shell squama technology there has also been and be more widely applied.Pilus Caprae seu Oviss divest scale layer
Benefit, mainly have the dyeability for improving Pilus Caprae seu Oviss, the antistatic property for improving Pilus Caprae seu Oviss, the snugness of fit for improving Pilus Caprae seu Oviss, change
The chemisorbed performance of kind Pilus Caprae seu Oviss, improve five aspects of preventing felting and shrinking of wood fabric performance.
China needs fine wool substantial amounts of to the ground import such as Australia, the country mainly to produce low-grade wool fiber every year,
And medium and high-quality wool fiber supply falls short of demand in China large market, in the state of extremely shortage.If there is method
Existing common and braid wool or half common and braid wool can be modified so as to similar to the performance of the fine wool of high-quality, so can be with
Common and braid wool raw material relatively low for relative mass is used, replaces fine wool to carry out textile manufacturing, it is possible to create bigger
Social value, creates significant economic benefit and social benefit.So, wool fiber of poor quality is carried out surface scale and is divested,
High-quality wool fiber needed for being modified on market has greatly potential commercial value, and China will also go into overdrive to carry out this side
The research work in face.
However, existing modified technique is not uniform to being optimized modified effect with a collection of wool fiber
, it is difficult to accomplish all wool fibers all perfectly to divest scale.Such as, in the wool fiber of same batch processing, have
Scale divests the fabulous wool fiber of effect, also has the wool fiber for almost not divesting scale, might have therebetween larger
Gap.Accordingly, it would be desirable to be estimated to modified effect, the preferable wool fiber of wherein treatment effect is screened out, which is obtained
Account for the percentage ratio of total amount.If divesting the good wool fiber of scale to be in the great majority in the Pilus Caprae seu Oviss of this batch processed, it is believed that change
The effect of property is good;, whereas if great majority all almost do not peel off scale in this batch wool fiber, then it is considered that modified
Effect bad.
The existing evaluation process to modified effect is carried out mainly or by manpower, is not only wasted time and energy, and assess
As a result affected by evaluator's subjective factorss larger, cause assess credible result degree not high.
Computer digital image process is exactly image to be received using computer, then enters the extraction of row information, adds
Work, pattern recognition and storage and the process of display.After computer has obtained the information of image, it is possible to carry out image to image
Enhancing, compression, recovery, segmentation, identification etc. various process.
Computer digital image process is a comparatively emerging subject, with developing rapidly for information technology, believes
There is the extensive application of Digital Image Processing in the fields such as breath process, e measurement technology and engineering technology.With computer section
The fast development of technology, digital image processing techniques achieve the progress of the formula of leaping.At the same time, at computer digital image
Manage contacting between Other subjects and intersect also increasingly extensive.As a kind of effective help mode, computer graphic image
Treatment technology has gradually been penetrated in the research work of Other subjects, such as arrives health care, Aero-Space, industry, military affairs etc.,
Its application more and more extensively, and increasingly plays its powerful effect.
Computer digital image process is to develop a very quick branch in the information processing technology.Due to computer hard
Developing rapidly in terms of part, the hardware condition of image processing techniquess development are strengthened.Within the time of nearly 30 years, calculate
Machine digital image processing techniques provide huge help for the research and development in each field, intersecting between Other subjects
Increasingly deepen.
With the fast development of the level of production, people are to the requirement in the requirement and level of comfort of the aesthetic aspect of dress ornament
More and more higher;And as production scale is increasing, the level of socializations of production process is improved, requirement of the dress ornament to raw material
More and more higher.Therefore, purely evaluate by people and differentiate that the quality and grade of product cannot meet the requirement of production again.
This is that often have very big subjective factorss to the judgement of product due to human eye, and the evaluation of mistake and discriminating will cause huge damage
Become estranged risk.It would therefore be desirable to a kind of new appraisal procedure so that accuracy, science and reliability that assessment has more.
Content of the invention
The technical problem to be solved is to provide a kind of digital picture stage division of wool scale layer, can be fast
Speed is equitably evaluated to wool modifying effect.
The technical solution adopted for the present invention to solve the technical problems is:A kind of digital picture of wool scale layer point is provided
Level method, comprises the following steps:
(1) digital picture to getting carries out denoising;
(2) by denoising after digital picture carry out binaryzation;
(3) to binaryzation after digital picture carry out the straight-line detection at Pilus Caprae seu Oviss edge, and choose suitable region;
(4) wool fiber in the appropriate area of selection is projected to and obtain in horizontal direction position residing for reaction wool scale
The waveform that puts;
(5) first derivative and second dervative of calculated wavy curve, according to first derivative and the value of second dervative
Determine peak point, wherein, it is 0 that peak point should meet first derivative, and second dervative is negative;
(6) spacing of adjacent peak point is calculated, and the spacing according to adjacent peak point is classified.
Step (1) carries out denoising using Gaussian smoothing filter method.
It is engaged and carrys out threshold value by human eye and edge line detection during binaryzation in step (2).
In step (3) to binaryzation after digital picture fitting a straight line is carried out by Hough transformation, extract Pilus Caprae seu Oviss fine
The both sides of dimension, complete the straight-line detection to Pilus Caprae seu Oviss edge.
Step (4) specifically include:Will choose appropriate area in wool fiber Image Reversal to horizontal direction, time
Each pixel that goes through on image, is integrated projection to image and obtains drop shadow curve.
Also include, in step (5), the step of peak point is screened, specially:Remove some highly with whole song
The meansigma methodss of line crest relatively;Remove in adjacent two close crests.
Beneficial effect
As a result of above-mentioned technical scheme, the present invention compared with prior art, has the following advantages that and actively imitates
Really:The present invention establishes a set of analysis of clearly sentencing for divesting effect with regard to wool scale and is classified, and coordinates digital image analysises to process skill
The use of art, research and development are identified the algorithm with classification to wool scale density, realize to wool fiber electron micrograph
Automatic classification function so as in real work can to process after the treatment effect of wool fiber carry out classification identification.?
On the basis of being classified, thus the effect of modification is made accurately, science, reliable assess, and then judge at this batch
Which kind of purposes the Pilus Caprae seu Oviss that managed can make in practicality.
Description of the drawings
Fig. 1 is the flow chart of the present invention;
Fig. 2 is Hough transformation detection of straight lines schematic diagram in embodiment;
Fig. 3 is the schematic diagram for selecting detection zone in embodiment;
Fig. 4 is the wool fiber digitized map for being turned to horizontal direction in embodiment;
Fig. 5 is wool fiber drop shadow curve figure in embodiment.
Specific embodiment
With reference to specific embodiment, the present invention is expanded on further.It should be understood that these embodiments are merely to illustrate the present invention
Rather than limit the scope of the present invention.In addition, it is to be understood that after the content for having read instruction of the present invention, people in the art
Member can be made various changes or modifications to the present invention, and these equivalent form of values equally fall within the application appended claims and limited
Scope.
Embodiments of the present invention are related to a kind of digital picture stage division of wool scale layer, specifically include following step
Suddenly:
(1) digital picture to getting carries out denoising.
A most important condition in digital picture application is exactly under noise background to search out image object.And eliminate image
The method of noise is image smoothing (smoothing).Image smoothing has two main purposes, the first to improve picture quality, its
Two is the feature for extracting object out.It is therefore desirable to an effective filtering mechanism is completing the lifting to picture quality and object
The extraction of feature.
During electromicroscopic photograph is shot, impurity always inevitably can be discharged into.Or in fiber micro-image
Acquisition procedure in, fiber edge occurs pseudo-side.For these phenomenons that fiber picture occurs, " noise should be adopted first
Remove " algorithm, the smoothing processing of image is carried out, the smooth effect which kind of algorithm is found through experiments is preferable.Conventional filtering is calculated
Method has simple smooth filtering, Gaussian smoothing filter, medium filtering etc..
It is the simple smooth process of image first.In simple smooth process, during algorithm uses convolution mask to image
Each pixel is processed one by one, then produces the filter effect of image.This process can be likened to as one by one mistake
Filter processes each pixel in source images, and carries out related data operation, finally gives data result, i.e., required
Smoothed image.
The Gaussian smoothing of image is to be smoothed one of method of image, is also based on the average basic think of in field
Road.And its simple smooth with image is where differing, and in the Gaussian smoothing of image, is carrying out the average image field
When different weights are given to the pixel of diverse location, then carry out data operation, then the smoothed image needed for obtaining again.With
The simple smooth of image compares, and when being smoothed to high-contrast image, the treatment effeciency of Gaussian smoothing is not high, smooths
Effect is not very good yet.But in smooth operation is needed, in the case of possessing the overall gray level characteristic distributions of source images,
Gaussian smoothing has very big advantage, can obtain preferable smooth effect.
Medium filtering is a kind of nonlinear filtering, and relative to other two kinds of wave filter, its advantage is:First, intermediate value
The effect that filtering reduces noise is obvious;Secondly, in the case where gray-value variation is smaller, medium filtering can be obtained very
Good smoothing processing result;Finally, complete edge details can be preferably protected in straight filtering in, rather than are flooded as mean filter
No details.
Present embodiment uses Gaussian smoothing filter.Show through many experiments, in Gaussian smoothing filter, simple average
In filtering and medium filtering, the noise reduction of Gaussian smoothing filter is optimal.
(2) by denoising after digital picture carry out binaryzation.
The binaryzation of image is exactly that the gray value of each pixel on image is set to 0 or 255, i.e., non-black i.e. white, figure
As upper only two kinds of colors.In Digital Image Processing, the binary conversion treatment of image is a highly important step, and this is due to figure
The binaryzation of picture is greatly reduced data volume in image, so as to highlight the profile of target, conveniently clarification of objective is carried out
Further extraction.
During image binaryzation, a threshold value is needed, the binaryzation degree of image is determined.Threshold value is to determine
Go out a scope, then the pixel on the image in this numerical value is arranged to 0, and the pixel outside this numerical value sets
It is set to 255.If certain pixel value on image is more than threshold value, then after converting, the gray value of the pixel is 255, as black
Color;Otherwise it is then 0, i.e. white.
For wool fiber image, required target is the density of wool surfaces scale, so what is desired is that squama
The edge of piece, so be black white image by the image binaryzation obtained after rim detection, to project the surface scale of fibre image
Feature.For image, in object and background, the maximum difference of debris is exactly gray level.The binaryzation of image is exactly logical
Cross and the gray scale of image is divided into different brackets, then the method by arranging threshold value is made a distinction background with object, so as to
Obtain the surface scale feature of the i.e. fiber of object needed for us.
In binarization, the size of threshold value can directly decide the effect of segmentation, when fixed too high of threshold value, accidentally go out
Existing object point will be taken as background so that whole picture is disorderly and unsystematic, is hard to tell object and background debris;If threshold value
Too low, contrary situation will occur.Object is dissolved in background, is not separated.Therefore, for the two-value of image
For change, it is of paramount importance to select a suitable threshold value so that divide rear backdrop minimum with the error of target.However, by
In Pilus Caprae seu Oviss electromicroscopic photograph, there are debris to affect unavoidably, and in different images, have the change of the conditions such as light, gray scale, it is difficult to make
The direct threshold value of computer.Therefore, the straight line searched out by human eye cooperation Hough transformation is needed in present embodiment, is determined
A fixed optimal threshold value, to ensure the accuracy of wool fiber classification.
(3) to binaryzation after digital picture carry out the straight-line detection at Pilus Caprae seu Oviss edge, and choose suitable region.
The edge both sides of wool fiber are close to straight line, in the research process for carrying out Pilus Caprae seu Oviss identification, can select using logical
The method that Hough transformation (Hough) carries out fitting a straight line is crossed, the both sides of wool fiber are extracted, so that it is determined that a suitable threshold
Value parameter, and it is easy to the later stage that wool fiber is carried out rotating to horizontal operation.
Hough transformation is to extract objective contour using a kind of transform domain, by the coordinate transform of the point on straight line was arrived
The coefficient domain of the straight line of point, and relation collinearly with straight line intersection is cleverly make use of, it is that the extraction problem of straight line is converted into meter
Number problem.Therefore, the extraction problem of image border can several Hough straight lines couple together group by the nothing through edge pixel point
Into closed area border.
Assume that straight line in O-xy planes, its equation are:Y=ux+v, wherein u and v be respectively straight line slope and
Intercept, for given straight line, a corresponding number is to (u, v), whereas if a given number is to (u, v), then correspondingly one
Several to (u, v) one-to-one corresponding, this relation on straight line y=ux+v and O-uv planes on bar straight line y=ux+v, i.e. O-xy planes
Referred to as Hough transformation.Therefore, in O-xy planes each point correspond to straight line, these straight lines all intersect at a bit (u,
V), but the slope of this straight line may be infinitely great, this linear equation is changed to polar equation therefore:Xcos α+ysin α=ρ,
In formula, ρ is distance of the straight line to coordinate origin, and α is the angle of straight line normal and X-axis, then, in O-xy plane coordinates one
Point in bar straight line and coordinate O- ρ α planes is corresponded.
Fig. 2 is Hough transformation detection of straight lines schematic diagram.According to the difference of the threshold value for manually selecting, it is straight that Hough transformation finds
Line can also change.Thus, when the edge line of wool fiber is more clearly detected, the scale feature of Pilus Caprae seu Oviss also obtain compared with
Good embodiment.It is possible thereby to determine a more accurately threshold value, after a threshold value is determined, need fine to Pilus Caprae seu Oviss manually
Dimension word picture carries out a regional choice, the region (see Fig. 3) that should now select edge clearly to be detected.
(4) wool fiber in the appropriate area of selection is projected to and obtain in horizontal direction position residing for reaction wool scale
The waveform that puts.
After obtaining reacting the binary image of wool scale feature, as long as wool fiber is projected to horizontal direction
On, it is possible to obtain the waveform for having reacted wool scale present position.And the position of its medium wave peak, it is exactly often that scale is located
Position.And if directly projected, due to the problem of angle, it is difficult to really reflect the true position residing for scale edge
Put.For this purpose, first having to a wool fiber digital picture is turned to horizontal direction (see Fig. 4), each pixel on traversing graph picture
Point, is integrated projection and obtains drop shadow curve (see Fig. 5) to image.
(5) first derivative and second dervative of calculated wavy curve, according to first derivative and the value of second dervative
Determine peak point, wherein, it is 0 that peak point should meet first derivative, and second dervative is negative.
The core thinking of crest detection algorithm is that the peak point of curve should meet first derivative for 0, and meets second order
Derivative is negative.The algorithm that present embodiment is adopted calculates first derivative diff_v [i] of curve first, is then converted
For -1 and 1, this is that needs are only its symbols as the concrete numerical value of first derivative is not meaningful, it is possible to find out former song
The monotonicity of line.Then for the point that the single order number of plies is 0 in, a part therein is not real crest, and only one
Order derivative is 0.So their first derivative is set to identical with the gradient direction at their places.
Then, when second dervative is calculated, if the second dervative of the point is -2, the direction of illustrative graph is at this
Point occurs by just becoming negative, that is, the wave crest point in virgin curve.And the position corresponding to wave crest point, just contain corresponding in artwork
Wool scale corresponding to position.
Yet with the scrambling of wool scale, the crest found by above-mentioned steps is simultaneously not all wool fiber squama
The position that the edge of piece is located, it is therefore desirable to which all crests for finding are screened.First have to reject some highly with entirely
The meansigma methodss of curve crest relatively.This is because these crests are only the edge projection of wool fiber obtain, and
It is not the reaction of the scale edge to wool surface.Second, in adjacent two close crests will be rejected, this is
Due to there is a scale edge due to the reason such as its pattern is irregular, may projection there are two adjacent ripples closely
Peak.Thus, it is possible to obtain more accurately, can react scale edge crest quantity.
(6) spacing of adjacent peak point is calculated, and the spacing according to adjacent peak point is classified.
According to the quantity that said method can obtain crest, the spacing of the spacing of crest, i.e. scale is so can be obtained by
d.After obtaining the spacing between scale, on the basis of a large amount of scale spacing datas that early stage is detected, which is concluded
And analysis, degree thus can be divested to the scale of wool fiber, and classification is gone out according to the value work done in the manner of a certain author of d.The mode of classification is specific as follows:
If d≤40, it is the first order;If 40 < d≤50, are the second level;If 50 < d≤60, are the third level;If 60 < d≤
70, it is the fourth stage;If d > 70, it is level V.Wherein level V is the superlative degree, that is, represent wool fiber scale and divest effect
Best grade;The first order is lowermost level, i.e., to divest effect poor for wool fiber scale.
If wherein it is especially noted that wool surface has almost divested scale completely, or be only left
In this case can directly should define the level as level V as a kind of special circumstances during minimal amount of scale vestiges.This be by
Drop shadow curve in now does not have obvious crest, and this may cause searching crest result inaccurate, and then the knot for causing to be classified
Really inaccurate.Therefore, hereinto in the case of there is no need to be classified using the method, directly define the level level V.
It is seen that, the present invention establishes a set of analysis of clearly sentencing for divesting effect with regard to wool scale and is classified, and coordinates numeral
The use of image analyzing and processing technology, research and development are identified the algorithm with classification to wool scale density, realize to wool fiber
Electron micrograph automatic classification function so as in real work can to process after the treatment effect of wool fiber enter
Row classification identification.On the basis of being classified, thus the effect of modification is made accurately, science, reliable assess, enter
And judge which kind of purposes the Pilus Caprae seu Oviss of the batch processing can make in practicality.
Claims (6)
1. the digital picture stage division of a kind of wool scale layer, it is characterised in that comprise the following steps:
(1) digital picture to getting carries out denoising;
(2) by denoising after digital picture carry out binaryzation;
(3) to binaryzation after digital picture carry out the straight-line detection at Pilus Caprae seu Oviss edge, and choose suitable region;
(4) wool fiber in the appropriate area of selection is projected to and obtains reacting wool scale present position in horizontal direction
Waveform;
(5) first derivative and second dervative of calculated wavy curve, determines according to the value of first derivative and second dervative
Peak point, wherein, it is 0 that peak point should meet first derivative, and second dervative is negative;
(6) spacing of adjacent peak point is calculated, and the spacing according to adjacent peak point is classified.
2. the digital picture stage division of wool scale layer according to claim 1, it is characterised in that step (1)
Denoising is carried out using Gaussian smoothing filter method.
3. the digital picture stage division of wool scale layer according to claim 1, it is characterised in that step (2)
It is engaged and carrys out threshold value by human eye and edge line detection during middle binaryzation.
4. the digital picture stage division of wool scale layer according to claim 1, it is characterised in that step (3)
In to binaryzation after digital picture fitting a straight line is carried out by Hough transformation, extract the both sides of wool fiber, complete to Pilus Caprae seu Oviss
The straight-line detection at edge.
5. the digital picture stage division of wool scale layer according to claim 1, it is characterised in that step (4)
Specifically include:Wool fiber Image Reversal in the appropriate area that will be chosen is to horizontal direction, each picture on traversing graph picture
Vegetarian refreshments, is integrated projection to image and obtains drop shadow curve.
6. the digital picture stage division of wool scale layer according to claim 1, it is characterised in that step (5)
In also include the step of peak point is screened, specially:Some are removed highly with the meansigma methodss of whole curve relatively
Crest;Remove in adjacent two close crests.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610966643.0A CN106503681B (en) | 2016-10-28 | 2016-10-28 | A kind of digital picture stage division of wool scale layer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610966643.0A CN106503681B (en) | 2016-10-28 | 2016-10-28 | A kind of digital picture stage division of wool scale layer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106503681A true CN106503681A (en) | 2017-03-15 |
CN106503681B CN106503681B (en) | 2019-05-03 |
Family
ID=58321799
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610966643.0A Expired - Fee Related CN106503681B (en) | 2016-10-28 | 2016-10-28 | A kind of digital picture stage division of wool scale layer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106503681B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112469994A (en) * | 2018-08-17 | 2021-03-09 | 日本制纸株式会社 | Method for analyzing structure containing fibers and inorganic particles |
CN113640445A (en) * | 2021-08-11 | 2021-11-12 | 贵州中烟工业有限责任公司 | Characteristic peak identification method based on image processing, computing equipment and storage medium |
CN115684737A (en) * | 2022-10-26 | 2023-02-03 | 常州同惠电子股份有限公司 | Algorithm for calculating waveform burrs |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8023742B2 (en) * | 2007-10-09 | 2011-09-20 | Microsoft Corporation | Local image descriptors using linear discriminant embedding |
CN103149210A (en) * | 2013-02-25 | 2013-06-12 | 东华大学 | System and method for detecting fabric cashmere content based on scale graphic features |
CN105678341A (en) * | 2016-02-19 | 2016-06-15 | 天纺标检测科技有限公司 | Wool cashmere recognition algorithm based on Gabor wavelet analysis |
-
2016
- 2016-10-28 CN CN201610966643.0A patent/CN106503681B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8023742B2 (en) * | 2007-10-09 | 2011-09-20 | Microsoft Corporation | Local image descriptors using linear discriminant embedding |
CN103149210A (en) * | 2013-02-25 | 2013-06-12 | 东华大学 | System and method for detecting fabric cashmere content based on scale graphic features |
CN105678341A (en) * | 2016-02-19 | 2016-06-15 | 天纺标检测科技有限公司 | Wool cashmere recognition algorithm based on Gabor wavelet analysis |
Non-Patent Citations (3)
Title |
---|
XIAN-JUN SHI ET AL.: "Fuzzy Classification of Animal Fibers Using Neuro-Fuzzy Classifier", 《2008 FIRST INTERNATIONAL CONFERENCE ON INTELLIGENT NETWORKS AND INTELLIGENT SYSTEMS》 * |
石先军 等: "基于贝叶斯方法的山羊绒与细羊毛的鉴别", 《纺织学报》 * |
高丽: "基于数字图像处理的羊绒和羊毛识别模型的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112469994A (en) * | 2018-08-17 | 2021-03-09 | 日本制纸株式会社 | Method for analyzing structure containing fibers and inorganic particles |
CN113640445A (en) * | 2021-08-11 | 2021-11-12 | 贵州中烟工业有限责任公司 | Characteristic peak identification method based on image processing, computing equipment and storage medium |
CN113640445B (en) * | 2021-08-11 | 2024-06-11 | 贵州中烟工业有限责任公司 | Characteristic peak identification method based on image processing, computing device and storage medium |
CN115684737A (en) * | 2022-10-26 | 2023-02-03 | 常州同惠电子股份有限公司 | Algorithm for calculating waveform burrs |
CN115684737B (en) * | 2022-10-26 | 2023-11-17 | 常州同惠电子股份有限公司 | Algorithm for calculating waveform glitch |
Also Published As
Publication number | Publication date |
---|---|
CN106503681B (en) | 2019-05-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101840511B (en) | Method for extracting, matching and recognizing characteristics of finger veins | |
Sun et al. | Fabric wrinkle characterization and classification using modified wavelet coefficients and support-vector-machine classifiers | |
CN101246543B (en) | Examiner identity identification method based on bionic and biological characteristic recognition | |
CN106503681A (en) | A kind of digital picture stage division of wool scale layer | |
CN103279745B (en) | A kind of face identification method based on half face multiple features fusion | |
CN101615245A (en) | Expression recognition method based on AVR and enhancing LBP | |
CN103164694A (en) | Method for recognizing human motion | |
CN105671769B (en) | A kind of dry and comfortable two-sided knitting fabric of polyester filament and preparation method thereof | |
CN104846571A (en) | Cotton tencel raising shell fabric dyeing and finishing processing method | |
CN203643345U (en) | Fabric crease resistance testing device for simulating practical dressing | |
CN104657983B (en) | A kind of fabric ball top Density Detection method filtered based on Gabor | |
CN105506194A (en) | Shorn sheepskin processing method and shorn sheepskin processed by method | |
CN106846396B (en) | The fabric pilling grade evaluation method of view-based access control model attention mechanism | |
Jabłońska et al. | Country-specific determinants of textile industry development in Poland: comparative analysis of the years 2007 and 2017 | |
Guo et al. | Multi-criteria decision making under uncertainty for Personality-driven Modern design | |
CN105844618A (en) | Image processing and characteristic extraction method of evaluating clothes wearing wrinkling degree | |
CN203373459U (en) | Light polyester fiber with high gap | |
Mo et al. | Research on image preprocessing for iris recognition | |
CN204661968U (en) | A kind of cleaning function weft knitting suede nap fabric | |
CN107190106A (en) | The production method of two layers of imitative head layer double-colored burnished leather naturally modelled after an antique | |
Lee et al. | A study on representation of 3D virtual fabric simulation with drape image analysis II-focus on the comparison between real clothing and 3D virtual clothing | |
Jayalakshmi et al. | Computer aided diagnostic support system for skin cancer using ELM classifier | |
CN101054606B (en) | Post processing method for leather pattern | |
CN110197114A (en) | A kind of automatic identifying method and device of full brain range single neuron aixs cylinder synaptic knob | |
Aragwal | Interaction of textile parameters, wash-ageing and use of fabric spftener during the laundry with mechanical properties of the knitted fabrics and correlation with textile hand |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190503 Termination date: 20211028 |
|
CF01 | Termination of patent right due to non-payment of annual fee |