CN110070537A - The granularity of still image particle and the intelligent identification Method of sphericity and device - Google Patents
The granularity of still image particle and the intelligent identification Method of sphericity and device Download PDFInfo
- Publication number
- CN110070537A CN110070537A CN201910339697.8A CN201910339697A CN110070537A CN 110070537 A CN110070537 A CN 110070537A CN 201910339697 A CN201910339697 A CN 201910339697A CN 110070537 A CN110070537 A CN 110070537A
- Authority
- CN
- China
- Prior art keywords
- particle
- original image
- noise
- image
- sphericity
- 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
- 239000002245 particle Substances 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000006243 chemical reaction Methods 0.000 claims abstract description 27
- 230000009467 reduction Effects 0.000 claims abstract description 19
- 238000009499 grossing Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 8
- 238000005259 measurement Methods 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 239000004568 cement Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000004005 microsphere Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000399 optical microscopy Methods 0.000 description 2
- 238000004062 sedimentation Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 206010019133 Hangover Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000007864 aqueous solution Substances 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006555 catalytic reaction Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000002296 dynamic light scattering Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 239000002778 food additive Substances 0.000 description 1
- 235000013373 food additive Nutrition 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000001000 micrograph Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000002086 nanomaterial Substances 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 229920002545 silicone oil Polymers 0.000 description 1
- 238000005245 sintering Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/13—Edge detection
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
Present applicant proposes the intelligent identification Methods and device of a kind of granularity of still image particle and sphericity, wherein, method includes: the original image by obtaining shooting, the conversion proportion ruler of original image is calculated, noise reduction is carried out to original image using Gaussian smoothing model, obtain noise-reduced image, edge extracting is carried out to noise-reduced image using canny Boundary extracting algorithm, the fitting of hough circle is carried out to the noise-reduced image after edge extracting, obtain the length in pixels of diameter corresponding to each fitting circle, the length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle is subjected to product, obtain the granularity of particle.Noise-reduced image after edge extracting is fitted using least square method, show that each fits the position of elliptical long axis and short axle and central point, calculates the oval coefficient of each fitted ellipse, the sphericity of particle can be obtained.Hereby it is achieved that the automatic identification of still image method, improves the granularity of still image method identification particle and the detection accuracy of sphericity.
Description
Technical field
This application involves the intelligence of the granularity and sphericity of image identification technical field more particularly to a kind of still image particle
It can recognition methods and device.
Background technique
The granularity and sphericity of particle determine many key properties of particle, not only influence electricity, optics, the power of particle
The performances such as, heat transfer, catalysis, have an effect on the performances such as density, condensation degree, flowing, transport, mixing, molding and the sintering of particle, relate to
And the application fields such as food manufacturing, drug production, mineral processing, life science.For example, the sphericity of food additives particle is determined
Determine its mobility；The granularity of drug granule determines the degree of absorption of human body；The granularity of cement determines the setting time of cement；It is single
The granularity of molecule handle bead determines the therapeutic effect etc. of drug.By the granularity sphericity for measuring these particles, so that it may
The performance of product is analyzed, and then actual production is preferably improved and optimized.
Currently, the measurement method of traditional grain graininess sphericity include sieve method, sedimentation, electric-resistivity method, dynamic optical dissipate
Penetrate method, laser method and image method etc..The result of sieve method is affected by human factor and sieve pore deformation；The sedimentation testing time
It is long, as a result vulnerable to such environmental effects；Electric-resistivity method is not suitable for the ultra-fine sample of measurement and wide distribution samples；Dynamic light scattering method measurement
The nano material error of width distribution is larger；The measurement result of laser method is affected by distributed model and instrument involves great expense.
And image method is with the continuous development of machine vision technique, the grain graininess sphericity based on digital image processing techniques measures system
System is continuously available the receiving and approval of people with its fast and accurately feature.Whether move, schemes according to particle in measurement process
As method can be divided into still image method and two kinds of dynamic image method.Compared with dynamic image method, still image method have collection capacity it is big,
In collection process without particle hangover and adhesion overlapping phenomenon, acquisition image clearly and particle dispersion is high the advantages that, therefore obtain
Widely application.
But when existing still image method measurement grain graininess sphericity, there are biggish human error, measurement accuracy
It need to be improved.
Summary of the invention
The application proposes the granularity of still image particle and the intelligent identification Method and device of sphericity, existing for solving
The granularity of particle and the larger technical problem of sphericity detection error in technology, realize particle granularity and sphericity it is high-precision
Spend automatic measurement.
The application first aspect embodiment proposes a kind of granularity of still image particle and the intelligent recognition side of sphericity
Method, comprising:
The original image of shooting is obtained, and the conversion proportion ruler of the original image is calculated；
Noise reduction is carried out to the original image using Gaussian smoothing model, obtains noise-reduced image；
Edge extracting is carried out to the noise-reduced image using canny Boundary extracting algorithm；
The fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains straight corresponding to each fitting circle
The length in pixels of diameter；
The length in pixels of diameter corresponding to the conversion proportion ruler and each fitting circle is subjected to product, is obtained every
The granularity of a particle；
The noise-reduced image after edge extracting is fitted using least square method, obtains the long axis of each fitted ellipse
With the position of short axle and central point, the oval coefficient of each fitted ellipse is calculated, the sphericity of each particle is obtained.
The granularity of the particle of the embodiment of the present application and the intelligent identification Method of sphericity, by the original graph for obtaining shooting
Picture, and the conversion proportion ruler of original image is calculated, noise reduction is carried out to original image using Gaussian smoothing model, obtains noise reduction
Image carries out edge extracting to noise-reduced image using canny Boundary extracting algorithm,
The fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains diameter corresponding to each fitting circle
The length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle is carried out product, obtains each particle by length in pixels
Granularity.In addition, being fitted to the noise-reduced image after edge extracting using least square method, the long axis of each fitted ellipse is obtained
With the position of short axle and central point, the oval coefficient of each fitted ellipse is calculated, the sphericity of each particle is obtained.As a result,
The automatic identification for realizing still image method improves the granularity and spherical shape of still image particle without excessive manual operation
The detection accuracy of degree.
The application second aspect embodiment proposes a kind of intelligent identification device of still image grain graininess sphericity, packet
It includes:
Module is obtained, for obtaining the original image of shooting, and the conversion proportion ruler of the original image is calculated；
Noise reduction module obtains noise-reduced image for carrying out noise reduction to the original image using Gaussian smoothing model；
Edge extracting module, for carrying out edge extracting to the noise-reduced image using canny Boundary extracting algorithm；
Fitting module obtains each fitting for carrying out the fitting of hough circle to the noise-reduced image after edge extracting
The length in pixels of the corresponding diameter of circle；
Granular Computing module, for the pixel of the conversion proportion ruler and diameter corresponding to each fitting circle is long
Degree carries out product, obtains the granularity of each particle；
Sphericity computing module is obtained each for being fitted to the noise-reduced image after edge extracting using least square method
The long axis and short axle of a fitted ellipse and the position of central point, calculate the oval coefficient of each fitted ellipse, obtain each
The sphericity of grain.
The granularity of the particle of the embodiment of the present application and the intelligent identification device of sphericity, by the original graph for obtaining shooting
Picture, and the conversion proportion ruler of original image is calculated, noise reduction is carried out to original image using Gaussian smoothing model, obtains noise reduction
Image carries out edge extracting to noise-reduced image using canny Boundary extracting algorithm,
The fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains diameter corresponding to each fitting circle
The length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle is carried out product, obtains each particle by length in pixels
Granularity.In addition, being fitted to the noise-reduced image after edge extracting using least square method, the long axis of each fitted ellipse is obtained
With the position of short axle and central point, the oval coefficient of each fitted ellipse is calculated, the sphericity of each particle is obtained.As a result,
The automatic identification for realizing still image method improves the granularity and spherical shape of still image particle without excessive manual operation
The detection accuracy of degree.
The additional aspect of the application and advantage will be set forth in part in the description, and will partially become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is a kind of granularity of still image particle provided by the embodiment of the present application and the intelligent identification Method of sphericity
Flow diagram；
Fig. 2 is a kind of granularity of still image particle provided by the embodiment of the present application and the intelligent identification Method of sphericity
Schematic diagram；
Fig. 3 is a kind of granularity of still image particle provided by the embodiment of the present application and the intelligent identification device of sphericity
Structural schematic diagram.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
Below with reference to the accompanying drawings the granularity of the still image particle of the embodiment of the present application and the intelligent recognition side of sphericity are described
Method and device.
Fig. 1 is a kind of granularity of still image particle provided by the embodiment of the present application and the intelligent identification Method of sphericity
Flow diagram.
As shown in Figure 1, this method may comprise steps of:
Step 101, the original image of shooting is obtained, and the conversion proportion ruler of original image is calculated.
In the embodiment of the present application, the sample of granularity to be detected and sphericity is placed under Powerful Light Microscope and is imaged, used
High speed camera observes visual field, and the particle in sample is kept to be in dispersity in camera imaging visual field, and it is suitable to be then adjusted to
Imaging magnification, be clearly captured the image of particle under the microscope, and all with TIF format, resolution ratio for 1600*1200 pixel
Image is saved, the original image of particle can be obtained.
It should be noted that the three-dimensional feature acquisition due to particle is relatively difficult, from multiple two-dimentional scales to original image
It is detected, can be used for constructing the three-dimensional information of particle, the three-dimensional geometry scale for approximate representation original image.The application
In embodiment, the shooting of axially different position is carried out to the discrete particle in sample, grain graininess and ball can be reflected by obtaining multiple
The original image of shape degree, so as to accurately reflect the information of particle three-dimensional scale.
Since the light source of Powerful Light Microscope is to carry out incidence with directional light, camera original image collected is complete
It is all the orthographic view of particle.
The granularity of particle in the embodiment of the present application and the intelligent identification Method of sphericity, suitable for detecting solution preservation
Sample (particle in such as aqueous solution or oil solution) and dry powder sample.Therefore, this method is suitable in water logging, oil immersion and air
The granularity and sphericity of sample particle captured by object lens detect, and the granularity and sphericity for being also applied for fluorescent grain detect.By
Then it is operated on optical microscopy, the visual field of imaging is limited, therefore the size of particle is no more than 5cm in sample.
As an example, subsphaeroidal microsphere sample is prepared first with microfluid auxiliary inner gel technique.By sample
Product are dispersed in silicone oil, are subsequently placed in and are observed on the objective table of inversion type optical microscopy and take pictures to obtain original image.
For corresponding scale in micrograph marker captured under different imaging magnifications.In addition, repeatedly being taken to same sample
Sample shoots the two-dimentional orthographic view of multiple subsphaeroidal microsphere samples, as shown in Fig. 2 (a).
In the embodiment of the present application, the obtained imaging magnification of original image is different due to shooting, mark on the original image
Ruler is not also identical.Therefore in order to which obtained particle length in pixels to be converted to the actual grain size of particle, need to pass through original graph
The scale of picture calculates length representated by unit pixel under current imaging magnification.It is, original image is amplified to pixel
Rank scale, surveyors' staff in original image across length in pixels S1, while record length represented by scale be R1,
Then conversion proportion ruler is R1/S1.
Step 102, noise reduction is carried out to institute's original image using Gaussian smoothing model, obtains noise-reduced image.
It will receive the different degrees of light between peripheral circuit and pixel itself during due to shooting original image
Electromagnetic interference, therefore inevitably there is noise, also, the difference of annoyance level in the original image that shooting obtains, shoot
The clarity of the image arrived is not also identical.Therefore, it is necessary to carry out noise reduction process to original image.
In the embodiment of the present application, original image is smoothed using Gaussian smoothing model, removes original image
Noise obtains noise-reduced image.
It should be noted that excessive smooth radius can lose image edge information, it is unfavorable for subsequent edge extracting, with
And too small smooth radius causes noise that cannot be inhibited well, therefore, in the present embodiment, uses smooth radius for 3-5
A pixel.
Continue taking the above example as an example, Gaussian smoothing model is utilized to the original image of acquisition, picture noise is removed, obtains
Noise-reduced image, as shown in Fig. 2 (b).
Step 103, edge extracting is carried out to noise-reduced image using canny Boundary extracting algorithm.
In the embodiment of the present application, when carrying out edge extracting to noise-reduced image using canny Boundary extracting algorithm, first to drop
Image of making an uproar carries out gray proces, obtains the grayscale image of image, secondly gaussian filtering is carried out to image, with the finite difference of single order local derviation
Divide to calculate the amplitude of the gradient of gray value of image and direction, and then non-maximum restraining is carried out to gradient magnitude, weeds out one
Divide the point of non-edge, finally detects and connect edge with dual threashold value-based algorithm.
For example, it after carrying out edge extracting to the noise-reduced image in Fig. 2 (b) using canny Boundary extracting algorithm, obtains
Particle marginal information, as shown in Fig. 2 (c).
Step 104, the fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains corresponding to each fitting circle
Diameter length in pixels.
In the embodiment of the present application, each pixel can use two dimension in image area in the noise-reduced image after edge extracting
Coordinate (x, y) is indicated, and can make numerous circle by each pixel, these circles can use its diameter d and the center of circle
(x0, y0) is expressed as (x0, y0, d), referred to as hough spatial representation.In the space hough, a circle can be expressed as one
It is a, and all circles for passing through the same point can be expressed as a series of continuous coordinates.It, can after sliding-model control
Coordinate grid is expressed as to discretization in the space hough with all circles that can indicate the marginal point in image space
Population density, the density determine that some position there are the probability that some is justified, is handled by thresholding, so that it may obtain all quasi-
The centre coordinate of the circle of conjunction and the length in pixels of diameter.
For example, carrying out the fitting of hough circle to the edge of particle, the pixel of the equivalent perspective plane diameter of microballoon can be obtained
Length, as shown in Fig. 2 (d).
It should be noted that hough circle extracts by the way of pure circle fitting in order to reduce calculation amount, in turn, calculate
The length in pixels of diameter corresponding to fitting circle out.
Step 105, the length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle is subjected to product, obtained
The granularity of grain.
In the embodiment of the present application, conversion proportion ruler and the length in pixels of diameter corresponding to each fitting circle are multiplied
Product, obtains the granularity of each particle.
It should be noted that after obtaining the granularity of multiple particles, calculating the flat of multiple grain graininess in same batch of sample
The average particle size of same batch sample can be obtained in mean value.
Step 106, the noise-reduced image after edge extracting is fitted using least square method, obtains each fitted ellipse
The position of long axis and short axle and central point, calculates the oval coefficient of each fitted ellipse, obtains the sphericity of particle.
In the embodiment of the present application, carried out on the basis of carrying out the fitting of hough circle to the noise-reduced image after edge extracting
Image border expansion, then fits the best length of each fitted ellipse in each border circular areas using least square method
The position of axis and short axle and central point, calculates the oval coefficient of fitted ellipse, i.e. the ratio a/b of long axis a and short axle b, then
Take the average value of multiple two-dimentional orthographic view ellipse coefficients, the approximate representation as particle three-dimensional sphericity.
It, can also be by the two-dimentional orthographic projection of multiple particles come close although sphericity reflects the feature in particle three-dimensional space
Like the sphericity of reflection particle.By carrying out ellipse fitting to the particle in Fig. 2 (d), being averaged for multiple particle ellipse coefficients is taken
Value, the as sphericity of particle.
Alternatively, the sphericity by the average value of the oval coefficient of the multiple orthographic views of particle, as particle.
Stringenter particle is required for granularity and sphericity, can be first fitted with hough circle, to obtain
The actual grain size of grain.Specifically, elliptical least square method fitting is carried out again on the basis of hough circle is fitted, sphericity is
For oval coefficient.
It can be to first carry out step 106 to obtain it is to be understood that executing sequence between step 104,105 and step 106
It to the sphericity of particle, then executes step 104 and step 105 obtains the granularity of particle, compares in the embodiment of the present application and do not limit
It is fixed.
The granularity of the particle of the embodiment of the present application and the intelligent identification Method of sphericity, by the original graph for obtaining shooting
Picture, and the conversion proportion ruler of original image is calculated, noise reduction is carried out to original image using Gaussian smoothing model, obtains noise reduction
Image carries out edge extracting to noise-reduced image using canny Boundary extracting algorithm,
The fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains diameter corresponding to each fitting circle
The length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle is carried out product, obtains each particle by length in pixels
Granularity.Noise-reduced image after edge extracting is fitted using least square method, obtain the long axis of each fitted ellipse with it is short
The position of axis and central point calculates the oval coefficient of each fitted ellipse, obtains the sphericity of each particle.Hereby it is achieved that
The automatic identification of still image method improves the granularity and sphericity of still image particle without excessive manual operation
Detection accuracy.
In order to realize above-described embodiment, the application also proposed a kind of granularity of still image particle and the intelligence of sphericity
Identification device.Fig. 3 is a kind of granularity of still image particle provided by the embodiments of the present application and the intelligent identification device of sphericity
Structural schematic diagram.
As shown in figure 3, the device includes: to obtain module 110, noise reduction module 120, edge extracting module 130, fitting module
140, Granular Computing module 150 and sphericity computing module 160.
Module 110 is obtained, for obtaining the original image of shooting, and the conversion proportion ruler of original image is calculated.
Noise reduction module 120 obtains noise-reduced image for carrying out noise reduction to original image using Gaussian smoothing model.
Edge extracting module 130, for carrying out edge extracting to noise-reduced image using canny Boundary extracting algorithm.
Fitting module 140 obtains each fitting for carrying out the fitting of hough circle to the noise-reduced image after edge extracting
The length in pixels of the corresponding diameter of circle.
Granular Computing module 150, for by the length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle into
Row product obtains the granularity of each particle.
Sphericity computing module 160 is obtained every for being fitted to the noise-reduced image after edge extracting using least square method
The position of one elliptical long axis and short axle and central point, calculates the oval coefficient of each fitted ellipse, obtains each particle
Sphericity.
As a kind of possible implementation, module 110 is obtained, is specifically used for:
The particle is shot from axially different position, obtains original image.
As alternatively possible implementation, module 110 is obtained, can also be specifically used for:
The original image is amplified to pixel scale scale, surveyors' staff in the original image across pixel
Length, while physical length represented by the scale is recorded, the ratio for calculating physical length and length in pixels obtains described turn
Change scale bar.
As alternatively possible implementation, wherein original image is the orthographic view of particle.
As alternatively possible implementation, the size of each particle is respectively less than 5cm.
The granularity of the particle of the embodiment of the present application and the intelligent identification device of sphericity, by the original graph for obtaining shooting
Picture, and the conversion proportion ruler of original image is calculated, noise reduction is carried out to original image using Gaussian smoothing model, obtains noise reduction
Image carries out edge extracting to noise-reduced image using canny Boundary extracting algorithm,
The fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains diameter corresponding to each fitting circle
The length in pixels of diameter corresponding to conversion proportion ruler and each fitting circle is carried out product, obtains each particle by length in pixels
Granularity.Noise-reduced image after edge extracting is fitted using least square method, obtain the long axis of each fitted ellipse with it is short
The position of axis and central point calculates the oval coefficient of each fitted ellipse, obtains the sphericity of each particle.Hereby it is achieved that
The automatic identification of still image method improves the granularity and sphericity of still image particle without excessive manual operation
Detection accuracy.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present application, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware in another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized: have for data-signal is realized the logic gates of logic function from
Logic circuit is dissipated, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application
System, those skilled in the art can be changed above-described embodiment, modify, replace and become within the scope of application
Type.
Claims (10)
1. a kind of granularity of still image particle and the intelligent identification Method of sphericity, which is characterized in that the method includes with
Lower step:
The original image of shooting is obtained, and the conversion proportion ruler of the original image is calculated；
Noise reduction is carried out to the original image using Gaussian smoothing model, obtains noise-reduced image；
Edge extracting is carried out to the noise-reduced image using canny Boundary extracting algorithm；
The fitting that hough circle is carried out to the noise-reduced image after edge extracting, obtains diameter corresponding to each fitting circle
Length in pixels；
The length in pixels of diameter corresponding to the conversion proportion ruler and each fitting circle is subjected to product, obtains particle
Granularity；
The noise-reduced image after edge extracting is fitted using least square method, obtain the long axis of each fitted ellipse with it is short
The position of axis and central point calculates the oval coefficient of each fitted ellipse, obtains the sphericity of particle.
2. recognition methods according to claim 1, which is characterized in that the original image for obtaining shooting, comprising:
The particle is shot from axially different position, obtains original image.
3. recognition methods according to claim 1, which is characterized in that the conversion ratio that the original image is calculated
Example ruler, comprising:
The original image is amplified to pixel scale scale, surveyors' staff in the original image across pixel it is long
Degree, while physical length represented by the scale is recorded, the ratio for calculating physical length and length in pixels obtains the conversion
Scale bar.
4. recognition methods according to claim 1, which is characterized in that the original image is the orthographic view of particle.
5. recognition methods according to claim 1, which is characterized in that the size of each particle is respectively less than 5cm.
6. a kind of granularity of still image particle and the intelligent identification device of sphericity, which is characterized in that described device includes:
Module is obtained, for obtaining the original image of shooting, and the conversion proportion ruler of the original image is calculated；
Noise reduction module obtains noise-reduced image for carrying out noise reduction to the original image using Gaussian smoothing model；
Edge extracting module, for carrying out edge extracting to the noise-reduced image using canny Boundary extracting algorithm；
Fitting module obtains each fitting circle institute for carrying out the fitting of hough circle to the noise-reduced image after edge extracting
The length in pixels of corresponding diameter；
Granular Computing module, for by the length in pixels of diameter corresponding to the conversion proportion ruler and each fitting circle into
Row product obtains the granularity of each particle；
Sphericity computing module is obtained each for being fitted to the noise-reduced image after edge extracting using least square method
The long axis and short axle of a fitted ellipse and the position of central point, calculate the oval coefficient of each fitted ellipse, obtain each
The sphericity of grain.
7. identification device according to claim 6, which is characterized in that the acquisition module is specifically used for:
The particle is shot from axially different position, obtains original image.
8. identification device according to claim 6, which is characterized in that the acquisition module can also be specifically used for:
The original image is amplified to pixel scale scale, surveyors' staff in the original image across pixel it is long
Degree, while physical length represented by the scale is recorded, the ratio for calculating physical length and length in pixels obtains the conversion
Scale bar.
9. identification device according to claim 6, which is characterized in that the original image is the orthographic view of particle.
10. identification device according to claim 6, which is characterized in that the size of each particle is respectively less than 5cm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339697.8A CN110070537B (en) | 2019-04-25 | 2019-04-25 | Intelligent identification method and device for granularity and sphericity of static image particles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339697.8A CN110070537B (en) | 2019-04-25 | 2019-04-25 | Intelligent identification method and device for granularity and sphericity of static image particles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070537A true CN110070537A (en) | 2019-07-30 |
| CN110070537B CN110070537B (en) | 2021-10-15 |
Family
ID=67368977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910339697.8A Active CN110070537B (en) | 2019-04-25 | 2019-04-25 | Intelligent identification method and device for granularity and sphericity of static image particles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070537B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598577A (en) * | 2019-08-23 | 2019-12-20 | 山东钢铁股份有限公司 | Image processing and analyzing method for information mining of coke in residual iron of blast furnace hearth |
| CN111707587A (en) * | 2020-06-04 | 2020-09-25 | 核工业北京地质研究院 | Particle size statistical method |
| CN112365538A (en) * | 2020-10-13 | 2021-02-12 | 西安理工大学 | Efficient target detection method of automatic reeling system |
| CN112652010A (en) * | 2020-12-25 | 2021-04-13 | 安徽工业大学 | Pellet particle size detection method based on image enhancement and Hough transform |
| CN113191271A (en) * | 2021-04-30 | 2021-07-30 | 水利部长江勘测技术研究所 | Method for detecting surface particulate matter of weir dam based on deep learning |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040165767A1 (en) * | 2002-09-30 | 2004-08-26 | Gokturk Salih B. | Three-dimensional pattern recognition method to detect shapes in medical images |
| CN102589435A (en) * | 2012-03-02 | 2012-07-18 | 中南大学 | Efficient and accurate detection method of laser beam center under noise environment |
| CN103093223A (en) * | 2012-12-10 | 2013-05-08 | 北京航空航天大学 | Light spot image center quick locating method |
| CN105760848A (en) * | 2016-03-04 | 2016-07-13 | 蒋志平 | Pupil positioning method based on annular template convolution |
| CN105873716A (en) * | 2013-11-05 | 2016-08-17 | 千住金属工业株式会社 | Cu core ball, solder paste, formed solder, cu core column, and solder joint |
| CN105931277A (en) * | 2016-04-01 | 2016-09-07 | 天津工业大学 | Partial differential equation-based nano-particle size measurement method |
| CN106769701A (en) * | 2017-02-28 | 2017-05-31 | 合肥工业大学 | A kind of particle sphericity coaxial digital holography detection means and detection method |
| CN107894379A (en) * | 2017-11-14 | 2018-04-10 | 沈阳聚德视频技术有限公司 | A kind of high-performance ore grain size vision detection system based on intelligent vision |
| CN108335310A (en) * | 2018-01-10 | 2018-07-27 | 华侨大学 | A kind of portable particle shape particle size detection method and system |
| CN108710852A (en) * | 2018-05-21 | 2018-10-26 | 山东大学 | It is a kind of to limit the size distribution image recognition methods for shooting depth and system |
| CN108986126A (en) * | 2018-06-15 | 2018-12-11 | 哈尔滨工业大学 | The center of circle detection method of RANSAC algorithm is detected and improved based on Gauss curve fitting sub-pixel edge |
| CN109269951A (en) * | 2018-09-06 | 2019-01-25 | 山西智卓电气有限公司 | Floating tail-coal ash content, concentration, coarse granule detection method of content based on image |
-
2019
- 2019-04-25 CN CN201910339697.8A patent/CN110070537B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040165767A1 (en) * | 2002-09-30 | 2004-08-26 | Gokturk Salih B. | Three-dimensional pattern recognition method to detect shapes in medical images |
| CN102589435A (en) * | 2012-03-02 | 2012-07-18 | 中南大学 | Efficient and accurate detection method of laser beam center under noise environment |
| CN103093223A (en) * | 2012-12-10 | 2013-05-08 | 北京航空航天大学 | Light spot image center quick locating method |
| CN105873716A (en) * | 2013-11-05 | 2016-08-17 | 千住金属工业株式会社 | Cu core ball, solder paste, formed solder, cu core column, and solder joint |
| CN105760848A (en) * | 2016-03-04 | 2016-07-13 | 蒋志平 | Pupil positioning method based on annular template convolution |
| CN105931277A (en) * | 2016-04-01 | 2016-09-07 | 天津工业大学 | Partial differential equation-based nano-particle size measurement method |
| CN106769701A (en) * | 2017-02-28 | 2017-05-31 | 合肥工业大学 | A kind of particle sphericity coaxial digital holography detection means and detection method |
| CN107894379A (en) * | 2017-11-14 | 2018-04-10 | 沈阳聚德视频技术有限公司 | A kind of high-performance ore grain size vision detection system based on intelligent vision |
| CN108335310A (en) * | 2018-01-10 | 2018-07-27 | 华侨大学 | A kind of portable particle shape particle size detection method and system |
| CN108710852A (en) * | 2018-05-21 | 2018-10-26 | 山东大学 | It is a kind of to limit the size distribution image recognition methods for shooting depth and system |
| CN108986126A (en) * | 2018-06-15 | 2018-12-11 | 哈尔滨工业大学 | The center of circle detection method of RANSAC algorithm is detected and improved based on Gauss curve fitting sub-pixel edge |
| CN109269951A (en) * | 2018-09-06 | 2019-01-25 | 山西智卓电气有限公司 | Floating tail-coal ash content, concentration, coarse granule detection method of content based on image |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598577A (en) * | 2019-08-23 | 2019-12-20 | 山东钢铁股份有限公司 | Image processing and analyzing method for information mining of coke in residual iron of blast furnace hearth |
| CN111707587A (en) * | 2020-06-04 | 2020-09-25 | 核工业北京地质研究院 | Particle size statistical method |
| CN112365538A (en) * | 2020-10-13 | 2021-02-12 | 西安理工大学 | Efficient target detection method of automatic reeling system |
| CN112652010A (en) * | 2020-12-25 | 2021-04-13 | 安徽工业大学 | Pellet particle size detection method based on image enhancement and Hough transform |
| CN113191271A (en) * | 2021-04-30 | 2021-07-30 | 水利部长江勘测技术研究所 | Method for detecting surface particulate matter of weir dam based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070537B (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070537A (en) | The granularity of still image particle and the intelligent identification Method of sphericity and device | |
| EP2085928B1 (en) | Detection of blobs in images | |
| Kovalev et al. | Texture anisotropy in 3-D images | |
| CN113689374B (en) | Method and system for determining surface roughness of plant leaf | |
| Xia et al. | Evaluation of focus measures for the autofocus of line scan cameras | |
| CN109300104A (en) | Angular-point detection method, device | |
| CN110992377A (en) | Image segmentation method, device, computer-readable storage medium and equipment | |
| CN111209822A (en) | Face detection method of thermal infrared image | |
| CN108230402A (en) | A kind of stereo calibration method based on trigone Based On The Conic Model | |
| CN112116553A (en) | Passive three-dimensional point cloud model defect identification method based on K-D tree | |
| Korzynska et al. | Segmentation of microscope images of living cells | |
| Streekstra et al. | Analysis of tubular structures in three-dimensional confocal images | |
| CN112883920A (en) | Point cloud deep learning-based three-dimensional face scanning feature point detection method and device | |
| Zakariah et al. | Image boundary, corner, and edge detection: past, present, and future | |
| Morales-Navarrete et al. | Automatic recognition and characterization of different non-parenchymal cells in liver tissue | |
| Castañeda et al. | Computational methods for analysis of dynamic events in cell migration | |
| CN114998980B (en) | Iris detection method and device, electronic equipment and storage medium | |
| EP2074591B1 (en) | Methods, system and computer program product for detecting a protrusion | |
| Ding et al. | Obtaining malignant melanoma indicators through statistical analysis of 3D skin surface disruptions | |
| Gao et al. | Somatic cells recognition by application of gabor feature-based (2D) 2PCA | |
| Majtner et al. | RSurf: the efficient texture-based descriptor for fluorescence microscopy images of HEp-2 cells | |
| Prasad et al. | Fast segmentation of sub-cellular organelles | |
| Forbes et al. | Methodologies for assessing local surface texture features that are relevant to cell attachment | |
| Im et al. | Tomo-PIV measurement of flow around an arbitrarily moving body with surface reconstruction | |
| Ding et al. | A computer assisted diagnosis system for malignant melanoma using 3D skin surface texture features and artificial neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |