CN107478656A - Paper pulp mixing effect method of determination and evaluation based on machine vision, device, system - Google Patents
Paper pulp mixing effect method of determination and evaluation based on machine vision, device, system Download PDFInfo
- Publication number
- CN107478656A CN107478656A CN201710676521.2A CN201710676521A CN107478656A CN 107478656 A CN107478656 A CN 107478656A CN 201710676521 A CN201710676521 A CN 201710676521A CN 107478656 A CN107478656 A CN 107478656A
- Authority
- CN
- China
- Prior art keywords
- mrow
- paper pulp
- msub
- image
- munderover
- 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
- 229920001131 Pulp (paper) Polymers 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000000694 effects Effects 0.000 title claims abstract description 30
- 238000002156 mixing Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 title claims description 7
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 239000000835 fiber Substances 0.000 claims abstract description 28
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 27
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000003756 stirring Methods 0.000 claims description 5
- 238000004898 kneading Methods 0.000 claims description 3
- 239000002002 slurry Substances 0.000 claims 1
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- -1 that is Polymers 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/85—Investigating moving fluids or granular solids
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention relates to a kind of paper pulp mixing effect methods of testing and evaluating based on machine vision, system：Methods described includes：Paper pulp image to be measured is obtained, the paper pulp is in and is stirred state；Paper pulp fiber target in the paper pulp image to be measured is detected using method for detecting image edge；The paper pulp fiber edge is handled using paper pulp evenness detection method, evaluates paper pulp mixing effect.The present invention compared with prior art, realizes on-line intelligence non-cpntact measurement, reduces labor intensity, and detection is accurate, improves production efficiency, saves labour, and whole detection process is not affected by human factors, and pulp quality has been effectively ensured.
Description
Technical field
The invention belongs to field of machine vision, and in particular to a kind of paper pulp mixing effect based on machine vision is detected with commenting
Valency method, system.
Background technology
Information technology has been widely used in paper industry, and the development of information technology is promoted and improved significantly
Automatic detection, automatically control and quality management level, paper-making industry is progressively taken leave of the inefficient epoch returned slowly.Due to computer
Image procossing and analytical technology make paper industry either in function still in the quality side of finished paper in the application of field of papermaking
Face all achieves unprecedented achievement.
In paper-making process, the quality of paper pulp mixing effect is directly connected to the quality of finished paper, but there is presently no one
The detecting system of kind on-line checking paper pulp mixing effect, can only be observed by human eye, take effort again.
The existing Machine Vision Detection to paper pulp image, belong to microscopic fields, what is predominantly detected is paper pulp under Microscopic Angle
The morphological parameters of fiber such as length, width, crimpness etc. have important influence for paper properties, but still paper pulp is not stirred
During stirring detection and appraisal procedure.
The content of the invention
For the deficiencies in the prior art, invention provides a kind of paper pulp mixing effect detection based on machine vision
With evaluation method, non-contact, the high-acruracy survey to paper pulp mixing effect are realized.
The present invention uses following technical scheme：
A kind of paper pulp mixing effect methods of testing and evaluating based on machine vision：
Paper pulp image to be measured is obtained, the paper pulp is in and is stirred state；
Paper pulp fiber target in the paper pulp image to be measured is detected using method for detecting image edge；
Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
Further, the paper pulp image to be measured of acquisition is converted into gray level image, and denoising is carried out to above-mentioned gray level image
Processing.
Further, for the gray level image after denoising, paper pulp figure is partitioned into using Minimum error threshold method
Fiber target as in.
Further, denoising is carried out to noisy gray level image using small wave converting method, specific steps include：
Select the small echo of setting and determine decomposition level N, N layer wavelet decompositions are carried out to noisy gray level image；Selection
The threshold function table of setting carries out the processing based on non-noise signal and noise signal to the wavelet coefficient of the N layers small echo；Obtain
The wavelet coefficient for including non-noise signal after noise signal is removed, the wavelet systems of non-noise signal are included described in reconstruct
Number, obtain removing the gray level image after noise.
Further, the Minimum error threshold method uses minimal error object function：
Optimal threshold t* is obtained by following formula：
Further, the paper pulp evenness detection method is the gray space correlation properties detection based on gray level co-occurrence matrixes
Method.
Further, gray level co-occurrence matrixes in the gray space correlation properties detection method based on gray level co-occurrence matrixes
P is：
Wherein, f (x, y) is paper pulp image to be split, and S is the pixel pair for having in the R of target area particular space relation
Set；
It with particular space relation, gray value is respectively g that molecule on the right of above formula equal sign, which is,1And g2Pixel pair number,
Denominator is the summation number of pixel pair, and # represents quantity；
According to formulaThe inverse difference moment of paper pulp image is obtained, paper pulp is evaluated according to inverse difference moment and stirred
The effect mixed.
Further, according to formulaThe energy value of paper pulp image is obtained, is evaluated according to energy value
The effect of paper pulp stirring.
Present invention also offers a kind of image processing apparatus, including processor and computer-readable recording medium, processor
For realizing each instruction；Computer-readable recording medium is used to store a plurality of instruction, and the instruction is suitable to by processor loading simultaneously
Perform following handle：
Paper pulp fiber target in paper pulp image to be measured is detected using method for detecting image edge；
Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
The present invention has also been proposed a kind of paper pulp mixing effect detection based on machine vision and evaluation system, including industrial phase
Machine, light source, image collecting device and image processing apparatus；The industrial camera and light source are located at the front of kneading pulper, work
The viewfinder range of industry camera includes paper pulp to be measured；Described industrial camera is connected with image collecting device, image collecting device with
Image processing apparatus connects；
Described image harvester includes first processor and the first computer-readable recording medium, first processor are used for
Realize each instruction；First computer-readable recording medium is used to store a plurality of instruction, and the instruction is suitable to be added by first processor
The processing for obtaining paper pulp image to be measured is carried and performs, the paper pulp is in and is stirred state；
Described image processing unit includes second processor and second computer readable storage medium storing program for executing, second processor are used for
Realize each instruction；Second computer readable storage medium storing program for executing is used to store a plurality of instruction, and the instruction is suitable to be added by second processor
Carry and perform following processing：
Paper pulp fiber target in paper pulp image to be measured is detected using method for detecting image edge；
Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
Further, described image harvester uses image pick-up card, and image pick-up card carries out A/D to the image of acquisition
Conversion, is sent to image processing apparatus.
Beneficial effects of the present invention：
The present invention compared with prior art, realizes on-line intelligence non-cpntact measurement, reduces labor intensity, and detection is accurate,
Production efficiency is improved, saves labour, and whole detection process is not affected by human factors, and pulpiness has been effectively ensured
Amount.
Brief description of the drawings
Accompanying drawing 1 is system structure diagram；
Accompanying drawing 2 is the workflow diagram that wavelet threshold shrinks Denoising Algorithm；
Accompanying drawing 3 is evaluation structure schematic diagram.
Embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings：
It is noted that described further below is all exemplary, it is intended to provides further instruction to the application.It is unless another
Indicate, all technologies used herein and scientific terminology are with usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in this manual using term "comprising" and/or " bag
Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
A kind of exemplary embodiments of the present invention are a kind of paper pulp mixing effect methods of testing and evaluating based on machine vision：
Paper pulp image to be measured is obtained, the paper pulp is in and is stirred state；
Paper pulp fiber target in the paper pulp image to be measured is detected using method for detecting image edge；
Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
Using the above method, the present invention proposes a kind of paper pulp mixing effect detection based on machine vision and is with evaluation
System, including industrial camera, light source, image collecting device and image processing apparatus；Industrial camera and light source are located at kneading pulper
Front, the viewfinder range of industrial camera includes paper pulp to be measured；Industrial camera is connected with image collecting device, image collecting device
It is connected with image processing apparatus.
Image collecting device includes first processor and the first computer-readable recording medium, and first processor is used to realize
Each instruction；First computer-readable recording medium is used to store a plurality of instruction, and the instruction is suitable to by first processor loading simultaneously
The processing for obtaining paper pulp image to be measured is performed, the paper pulp is in and is stirred state；
Image processing apparatus includes second processor and second computer readable storage medium storing program for executing, and second processor is used to realize
Each instruction；Second computer readable storage medium storing program for executing is used to store a plurality of instruction, and the instruction is suitable to by second processor loading simultaneously
Perform following handle：
Paper pulp fiber target in paper pulp image to be measured is detected using method for detecting image edge；
Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
Further, described image harvester uses image pick-up card, and image pick-up card carries out A/D to the image of acquisition
Conversion, is sent to image processing apparatus.
Image collecting device uses image pick-up card, and image pick-up card carries out A/D conversions to the image of acquisition, is sent to figure
As processing unit.
Industrial camera is using CCD industrial cameras；Light source is using LED light source.
The image that the camera of CCD industrial cameras amplifies to high magnified glass is acquired, through image pick-up card to image
A/D conversions are carried out, are converted into the digital picture that image processing apparatus can be handled；The image processing apparatus used in the present embodiment
Generally computer.
CCD industrial cameras are obtained in the paper pulp image to be measured being stirred under state, and original image is converted to gray-scale map
Picture, Denoising Algorithm is shunk by wavelet threshold denoising is carried out to gray level image, then using linear image Enhancement Method to figure
As carrying out enhancing processing, improve the definition of paper pulp on the whole.Minimal error threshold is carried out to the paper pulp image after enhancing again
Value segmentation, the fiber being partitioned into paper pulp, is further studied the distribution situation of fiber.
Wavelet threshold shrinks concretely comprising the following steps for denoising：
(1) select suitable small echo and determine decomposition level (N), it is small to carrying out N layers comprising noise two dimensional image afterwards
Wave Decomposition；(2) suitable threshold function table is selected to wavelet coefficient caused by the image useful signal of acquisition in (1) and noise signal
Handled；(3) remaining wavelet coefficient is exactly to have eliminated the noise letter that HFS is included after (2) are handled
Number, wavelet reconstruction processing then is carried out to remaining wavelet coefficient, finally gives the two dimensional image after removing noise.
Using concretely comprising the following steps for Minimum error threshold method：
Pixel in image is divided into background and the class C of target two by gray value with threshold value t0And C1, i.e. C0=0,1 ...,
T }, C1=t+1, t+2 ..., L-1 } (usual L=256).Then C0And C1The probability being each distributed is respectively：
Wherein piRepresent the probability that the pixel of gray value i in gray level image occurs, ω0+ω1=1, make ω (t)=ω0,
Then ω1=1- ω (t).
C0And C1The mean μ being each distributed0And μ1Respectively：
C0And C1The variances sigma being each distributed0 2And σ1 2Respectively：
Based on minimum classification error thought, minimal error object function J (t) is provided:
Optimal threshold t*It can be obtained by following formula：
Based on above-mentioned formula, the fiber target being partitioned into paper pulp, that is, paper pulp fiber edge.
Next, we evaluate paper pulp mixing effect using paper pulp evenness detection method processing paper pulp fiber edge.
Paper pulp IMAQ window is set as 512 × 512 pixels, actual acquisition area is about 4cm2, it is carried on the back
Scape is corrected to eliminate the irregular phenomenon of bias light；If f (x, y) is paper pulp segmentation figure picture, S is to have particular space in the R of target area
The set of the pixel pair of contact, then the gray level co-occurrence matrixes P for meeting certain space relation are：
Molecule on the right of above formula equal sign is for the pixel pair for being respectively g1 and g2 with certain spatial relationship, gray value
Number, (x1,y1) and (x2,y2) for the coordinate of the pixel on paper pulp segmentation figure picture, for the summation number of pixel pair, (# is represented denominator
Quantity).According to formula (1)With formula (2)Obtain paper pulp image
The value of inverse difference moment and energy, wherein i are g1, j g2.The effect of paper pulp stirring is judged according to inverse difference moment and the size of energy value,
Energy (ASM) reflects gradation of image and is evenly distributed degree；Inverse difference moment (IDM) reflects the homogeney of image texture, measures image
The number of texture localized variation.Inverse difference moment and energy are bigger, and paper pulp stirs more uniform, fiber dispersed distribution, and effect is better.Gray scale
Co-occurrence matrix method realizes that speed is fast, and real-time amount of calculation is small, and Detection results are good.
The present embodiment compared with prior art, realizes on-line intelligence non-cpntact measurement, reduces labor intensity, and detection is accurate
Really, production efficiency is improved, saves labour, and whole detection process is not affected by human factors, and paper pulp has been effectively ensured
Quality.
The preferred embodiment of the application is the foregoing is only, is not limited to the application, for the skill of this area
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent substitution, improvement etc., should be included within the protection domain of the application.
Claims (10)
- A kind of 1. paper pulp mixing effect methods of testing and evaluating based on machine vision：It is characterized in that：Paper pulp image to be measured is obtained, the paper pulp is in and is stirred state；Paper pulp fiber target in the paper pulp image to be measured is detected using method for detecting image edge；Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
- 2. according to the method for claim 1, it is characterised in that：The paper pulp image to be measured of acquisition is converted into gray level image, And denoising is carried out to above-mentioned gray level image.
- 3. according to the method for claim 2, it is characterised in that：For the gray level image after denoising, using minimal error Threshold segmentation method is partitioned into the fiber target in paper pulp image.
- 4. according to the method for claim 2, it is characterised in that：Noisy gray level image is carried out using small wave converting method Denoising, specific steps include：Select the small echo of setting and determine decomposition level N, N layer wavelet decompositions are carried out to noisy gray level image；Selection setting Threshold function table the processing based on non-noise signal and noise signal is carried out to the wavelet coefficient of the N layers small echo；Removed The wavelet coefficient for including non-noise signal after noise signal, the wavelet coefficient of non-noise signal is included described in reconstruct, is obtained Gray level image to after removal noise.
- 5. according to the method for claim 3, it is characterised in that described using the segmentation paper delivery of Minimum error threshold method Fiber target in slurry image includes：Pixel in image is divided into background and the class C of target two by gray value with threshold value t0And C1, That is C0={ 0,1 ..., t }, C1={ t+1, t+2 ..., L-1 }, then C0And C1The probability being each distributed is respectively：<mrow> <msub> <mi>&omega;</mi> <mn>0</mn> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mi>t</mi> </munderover> <msub> <mi>p</mi> <mi>i</mi> </msub> </mrow><mrow> <msub> <mi>&omega;</mi> <mn>1</mn> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> </mrow> <mrow> <mi>L</mi> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <msub> <mi>p</mi> <mi>i</mi> </msub> </mrow>Wherein piRepresent the probability that the pixel of gray value i in gray level image occurs, ω0+ω1=1, make ω (t)=ω0, then ω1 =1- ω (t), C0And C1The mean μ being each distributed0And μ1Respectively：<mrow> <msub> <mi>&mu;</mi> <mn>0</mn> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mi>t</mi> </munderover> <mi>i</mi> <mfrac> <msub> <mi>p</mi> <mi>i</mi> </msub> <msub> <mi>&omega;</mi> <mn>0</mn> </msub> </mfrac> </mrow><mrow> <msub> <mi>&mu;</mi> <mn>1</mn> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> </mrow> <mrow> <mi>L</mi> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <mi>i</mi> <mfrac> <msub> <mi>p</mi> <mi>i</mi> </msub> <msub> <mi>&omega;</mi> <mn>1</mn> </msub> </mfrac> </mrow>C0And C1The variances sigma being each distributed0 2And σ1 2Respectively：<mrow> <msubsup> <mi>&sigma;</mi> <mn>0</mn> <mn>2</mn> </msubsup> <mo>=</mo> <mfrac> <mn>1</mn> <msub> <mi>&omega;</mi> <mn>0</mn> </msub> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>0</mn> </mrow> <mi>t</mi> </munderover> <msub> <mi>p</mi> <mi>i</mi> </msub> <mi>g</mi> <msup> <mrow> <mo>(</mo> <mi>i</mi> <mo>-</mo> <msub> <mi>&mu;</mi> <mn>0</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow><mrow> <msubsup> <mi>&sigma;</mi> <mn>1</mn> <mn>2</mn> </msubsup> <mo>=</mo> <mfrac> <mn>1</mn> <msub> <mi>&omega;</mi> <mn>1</mn> </msub> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> </mrow> <mrow> <mi>L</mi> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <msub> <mi>p</mi> <mi>i</mi> </msub> <mi>g</mi> <msup> <mrow> <mo>(</mo> <mi>i</mi> <mo>-</mo> <msub> <mi>&mu;</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow>Based on minimum classification error thought, minimal error object function J (t) is provided:<mrow> <mi>J</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <mn>1</mn> <mo>+</mo> <mi>&omega;</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>&CenterDot;</mo> <mi>l</mi> <mi>o</mi> <mi>g</mi> <mfrac> <msubsup> <mi>&sigma;</mi> <mn>0</mn> <mn>2</mn> </msubsup> <msup> <mrow> <mo>&lsqb;</mo> <mi>&omega;</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>&rsqb;</mo> </mrow> <mn>2</mn> </msup> </mfrac> <mo>+</mo> <mo>&lsqb;</mo> <mn>1</mn> <mo>-</mo> <mi>&omega;</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>&rsqb;</mo> <mo>&CenterDot;</mo> <mi>l</mi> <mi>o</mi> <mi>g</mi> <mfrac> <msubsup> <mi>&sigma;</mi> <mn>1</mn> <mn>2</mn> </msubsup> <msup> <mrow> <mo>&lsqb;</mo> <mn>1</mn> <mo>-</mo> <mi>&omega;</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>&rsqb;</mo> </mrow> <mn>2</mn> </msup> </mfrac> </mrow>Optimal threshold t*It can be obtained by following formula：<mrow> <msup> <mi>t</mi> <mo>*</mo> </msup> <mo>=</mo> <mi>arg</mi> <mo>{</mo> <munder> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> <mrow> <mn>0</mn> <mo>&le;</mo> <mi>t</mi> <mo><</mo> <mi>L</mi> </mrow> </munder> <mi>J</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>}</mo> <mo>.</mo> </mrow> 1
- 6. according to the method for claim 5, it is characterised in that：The paper pulp evenness detection method is based on gray scale symbiosis square The gray space correlation properties detection method of battle array.
- 7. according to the method for claim 6, it is characterised in that：The gray space based on gray level co-occurrence matrixes is related special Gray level co-occurrence matrixes P is in property detection method：Wherein, f (x, y) is paper pulp image to be split, and S is the collection of the pixel pair in the R of target area with particular space relation Close；It with particular space relation, gray value is respectively g that molecule on the right of above formula equal sign, which is,1And g2Pixel pair number, denominator For the summation number of pixel pair, # represents quantity；According to formulaThe inverse difference moment of paper pulp image is obtained, evaluates what paper pulp stirred according to inverse difference moment Effect.
- 8. according to the method for claim 7, it is characterised in that：According to formulaObtain paper pulp figure The energy value of picture, the effect of paper pulp stirring is evaluated according to energy value.
- 9. a kind of image processing apparatus, it is characterised in that including processor and computer-readable recording medium, processor is used for real Now each instruction；Computer-readable recording medium is used to store a plurality of instruction, the instruction be suitable to be loaded by processor and performed with Lower processing：Paper pulp fiber target in paper pulp image to be measured is detected using method for detecting image edge；Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
- 10. a kind of detection of paper pulp mixing effect and evaluation system based on machine vision, it is characterised in that：Including industrial camera, Light source, image collecting device and image processing apparatus；The industrial camera and light source are located at the front of kneading pulper, industrial phase The viewfinder range of machine includes paper pulp to be measured；Described industrial camera is connected with image collecting device, image collecting device and image Processing unit connects；Described image harvester includes first processor and the first computer-readable recording medium, and first processor is used to realize Each instruction；First computer-readable recording medium is used to store a plurality of instruction, and the instruction is suitable to by first processor loading simultaneously The processing for obtaining paper pulp image to be measured is performed, the paper pulp is in and is stirred state；Described image processing unit includes second processor and second computer readable storage medium storing program for executing, and second processor is used to realize Each instruction；Second computer readable storage medium storing program for executing is used to store a plurality of instruction, and the instruction is suitable to by second processor loading simultaneously Perform following handle：Paper pulp fiber target in paper pulp image to be measured is detected using method for detecting image edge；Using the edge of paper pulp evenness detection method detection paper pulp fiber target, paper pulp mixing effect is evaluated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710676521.2A CN107478656B (en) | 2017-08-09 | 2017-08-09 | Paper pulp stirring effect detection and evaluation method, device and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710676521.2A CN107478656B (en) | 2017-08-09 | 2017-08-09 | Paper pulp stirring effect detection and evaluation method, device and system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107478656A true CN107478656A (en) | 2017-12-15 |
| CN107478656B CN107478656B (en) | 2021-02-12 |
Family
ID=60599758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710676521.2A Expired - Fee Related CN107478656B (en) | 2017-08-09 | 2017-08-09 | Paper pulp stirring effect detection and evaluation method, device and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107478656B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765433A (en) * | 2018-05-31 | 2018-11-06 | 西京学院 | One kind is for carrying high-precision leafy area measurement method |
| CN114632713A (en) * | 2022-05-18 | 2022-06-17 | 山东博汇纸业股份有限公司 | Paper pulp thickness detection system for double-sided copper plate paperboard based on visual sensor |
| CN117212182A (en) * | 2023-11-07 | 2023-12-12 | 尚宝罗江苏节能科技股份有限公司 | Low-pulse pulp pump for papermaking pulp and detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2689238A1 (en) * | 1992-03-30 | 1993-10-01 | Scanera Sc | Optical sensor for particle size measurement in textile industry - is focused on observation area where input and output particle samples are presented while microprocessor with comparator controls refiner |
| JPH0777502A (en) * | 1993-09-07 | 1995-03-20 | Ishikawajima Harima Heavy Ind Co Ltd | Pulp fiber observation equipment |
| CN102692251A (en) * | 2012-05-14 | 2012-09-26 | 山东轻工业学院 | FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) based system and method for rapidly measuring embedded pulp fiber morphological parameters |
| CN103424409A (en) * | 2013-04-12 | 2013-12-04 | 安徽工业大学 | Vision detecting system based on DSP |
| CN103454216A (en) * | 2013-09-07 | 2013-12-18 | 齐鲁工业大学 | Method and system for calibrating measurement resolution of runner-type pulp fiber measuring system on line |
| CN105260559A (en) * | 2015-10-31 | 2016-01-20 | 齐鲁工业大学 | Paper pulp fiber morphology parameter calculation method based on contour area and contour refinement |
-
2017
- 2017-08-09 CN CN201710676521.2A patent/CN107478656B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2689238A1 (en) * | 1992-03-30 | 1993-10-01 | Scanera Sc | Optical sensor for particle size measurement in textile industry - is focused on observation area where input and output particle samples are presented while microprocessor with comparator controls refiner |
| JPH0777502A (en) * | 1993-09-07 | 1995-03-20 | Ishikawajima Harima Heavy Ind Co Ltd | Pulp fiber observation equipment |
| CN102692251A (en) * | 2012-05-14 | 2012-09-26 | 山东轻工业学院 | FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) based system and method for rapidly measuring embedded pulp fiber morphological parameters |
| CN103424409A (en) * | 2013-04-12 | 2013-12-04 | 安徽工业大学 | Vision detecting system based on DSP |
| CN103454216A (en) * | 2013-09-07 | 2013-12-18 | 齐鲁工业大学 | Method and system for calibrating measurement resolution of runner-type pulp fiber measuring system on line |
| CN105260559A (en) * | 2015-10-31 | 2016-01-20 | 齐鲁工业大学 | Paper pulp fiber morphology parameter calculation method based on contour area and contour refinement |
Non-Patent Citations (2)
| Title |
|---|
| 侯北平等: "基于计算机视觉的纸浆纤维特性检测与研究", 《中国造纸学报》 * |
| 苏方远等: "燃料电池用炭纤维纸前驱体的匀度表征与控制", 《化工新型材料》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765433A (en) * | 2018-05-31 | 2018-11-06 | 西京学院 | One kind is for carrying high-precision leafy area measurement method |
| CN114632713A (en) * | 2022-05-18 | 2022-06-17 | 山东博汇纸业股份有限公司 | Paper pulp thickness detection system for double-sided copper plate paperboard based on visual sensor |
| CN117212182A (en) * | 2023-11-07 | 2023-12-12 | 尚宝罗江苏节能科技股份有限公司 | Low-pulse pulp pump for papermaking pulp and detection method |
| CN117212182B (en) * | 2023-11-07 | 2024-01-26 | 尚宝罗江苏节能科技股份有限公司 | Low-pulse pulp pump for papermaking pulp and detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107478656B (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104657984B (en) | The extraction method of three-D ultrasonic mammary gland total volume interesting image regions | |
| CN107230203B (en) | Casting defect identification method based on human eye visual attention mechanism | |
| CN108765412A (en) | A kind of steel strip surface defect sorting technique | |
| CN107507173A (en) | A kind of full slice image without refer to intelligibility evaluation method and system | |
| WO2008005426A2 (en) | Computer-aided pathological diagnosis system | |
| CN106815819B (en) | More strategy grain worm visible detection methods | |
| CN108416766A (en) | Bilateral incidence type light guide plate defective vision detection method | |
| CN109241867B (en) | Method and device for recognizing digital rock core image by adopting artificial intelligence algorithm | |
| CN107478656A (en) | Paper pulp mixing effect method of determination and evaluation based on machine vision, device, system | |
| CN109191434A (en) | Image detecting system and detection method in a kind of cell differentiation | |
| CN105510364A (en) | Nondestructive testing system for industrial part flaws based on X rays and detection method thereof | |
| Bellens et al. | Evaluating conventional and deep learning segmentation for fast X-ray CT porosity measurements of polymer laser sintered AM parts | |
| CN108052909B (en) | Thin fiber cap plaque automatic detection method and device based on cardiovascular OCT image | |
| CN108648199B (en) | Ultrasonic phased array NDT image segmentation method based on watershed and CV models | |
| Chang et al. | Automatic brain MR image denoising based on texture feature-based artificial neural networks | |
| Martinez-Garcia et al. | Automated 3D tree-ring detection and measurement from X-ray computed tomography | |
| Konstandinou et al. | Multifeature quantification of nuclear properties from images of H&E‐stained biopsy material for investigating changes in nuclear structure with advancing CIN grade | |
| CN113628170A (en) | Laser line extraction method and system based on deep learning | |
| CN116883987A (en) | Pointer instrument reading identification method for unmanned inspection of transformer substation | |
| CN112396618A (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| Ziabari et al. | Simurgh: A Framework for CAD-Driven Deep Learning Based X-Ray CT Reconstruction | |
| Dulecha et al. | Crack detection in single-and multi-light images of painted surfaces using convolutional neural networks | |
| Gun et al. | A contour detector with improved corner detection | |
| CN115984246A (en) | Defect rapid detection method and device based on machine vision, equipment and storage medium | |
| Yu et al. | Analysis and processing of decayed log CT image based on multifractal theory |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210212 Termination date: 20210809 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |