CN106780347A - A kind of loquat early stage bruise discrimination method based on OCT image treatment - Google Patents
A kind of loquat early stage bruise discrimination method based on OCT image treatment Download PDFInfo
- Publication number
- CN106780347A CN106780347A CN201710071158.1A CN201710071158A CN106780347A CN 106780347 A CN106780347 A CN 106780347A CN 201710071158 A CN201710071158 A CN 201710071158A CN 106780347 A CN106780347 A CN 106780347A
- Authority
- CN
- China
- Prior art keywords
- image
- cell
- loquat
- bruise
- pixel
- 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
- 241001092070 Eriobotrya Species 0.000 title claims abstract description 44
- 235000009008 Eriobotrya japonica Nutrition 0.000 title claims abstract description 43
- 208000034656 Contusions Diseases 0.000 title claims abstract description 41
- 208000034526 bruise Diseases 0.000 title claims abstract description 41
- 238000012850 discrimination method Methods 0.000 title claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000011946 reduction process Methods 0.000 claims abstract description 4
- 210000004027 cell Anatomy 0.000 claims description 65
- 238000001914 filtration Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 5
- 230000000717 retained effect Effects 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 210000001339 epidermal cell Anatomy 0.000 claims description 3
- 210000002615 epidermis Anatomy 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 20
- 238000001514 detection method Methods 0.000 abstract description 9
- 235000013399 edible fruits Nutrition 0.000 abstract description 4
- 238000007920 subcutaneous administration Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 10
- 210000001519 tissue Anatomy 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000003306 harvesting Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- FNMKZDDKPDBYJM-UHFFFAOYSA-N 3-(1,3-benzodioxol-5-yl)-7-(3-methylbut-2-enoxy)chromen-4-one Chemical compound C1=C2OCOC2=CC(C2=COC=3C(C2=O)=CC=C(C=3)OCC=C(C)C)=C1 FNMKZDDKPDBYJM-UHFFFAOYSA-N 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 206010052428 Wound Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 238000005469 granulation Methods 0.000 description 1
- 230000003179 granulation Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000869 mutational effect Effects 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4023—Decimation- or insertion-based scaling, e.g. pixel or line decimation
-
- G06T5/70—
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10101—Optical tomography; Optical coherence tomography [OCT]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The invention discloses a kind of loquat early stage bruise discrimination method based on OCT image treatment.Gather the SD OCT images with cell image details of loquat, use bicubic interpolation algorithm, down-sampled downscaled images resolution ratio is carried out to image, carry out Gaussian Blur noise reduction process, extract the line of demarcation of loquat target and background, take the peak in line of demarcation and as a reference point, according to reference point so that line of demarcation is deformed into along the straight line of reference point, mean filter is carried out to image, binary conversion treatment is carried out to image, binary Images Processing is obtained into the corresponding cell compartment of each cell, the result that bruise differentiates is obtained by being analyzed to calculate to cell compartment.The inventive method realizes the full-automatic detection of the early stage bruise of loquat fruit, and completes the subcutaneous cell mark of bruise tissue and differentiate, improves detection efficiency, is that loquat interior quality on-line checking establishes technical foundation.
Description
Technical field
The invention belongs to fruit internal quality Aulomatizeted Detect field, it is related to OCT image processing method, more particularly, to
A kind of loquat early stage bruise discrimination method based on OCT image treatment.
Background technology
Loquat is one of peculiar fruit special product of China, its inside quality in harvesting, sale, transport, storing process
Lossless method for quick is the technical problem underlying that loquat industry development faces.Loquat in each industry sales process, easily
External force damage is received, the putrid and deteriorated of later stage is caused.The bruise of loquat possibly be present at harvesting, storage, transport, packaging etc. each
Link, is difficult to be noticeable in sale early stage.Loquat shelf life after bruise is greatly shortened, due to cyto-architectural breakage, tissue
Progressively brown stain, has had a strong impact on the satisfaction and repurchase rate of consumer.
In Non-Destructive Testing loquat internal structure, spectroscopic methodology or high light spectrum image-forming are generally used, it is necessary to large scale equipment is protected
Comprehensive collection of spectral information is demonstrate,proved, more detection time and costs are expended, and there are certain technical requirements to testing staff, and
High spectrum image is difficult really to reflect its inner case that spectral signature has certain skew with the change of loquat species.Spectral domain
Optical coherent chromatographic imaging (SD-OCT) represents internal its structural form and distribution, mesh by the optical interference characteristic of measurement of species
Preceding SD-OCT images have been used to identification, quantitative measurment, the Qualitative Identification of the multiple tissues of human body, and report shows that image can understand
Represent the hierarchical structure of biological tissue.In agricultural, cultivation field, mainly application has current OCT image method：Observe the epidermis of apple
Inside eucaryotic cell structure, the growth of observation of plant blade of structure, difference seawater nucleated pearl and fresh water pipless pearl, observation seed
Defect etc..The method is used for loquat industry, with wide application prospect.
Because in industry application, loquat OCT image contrast is small, and feature is not obvious, using artificial cognition, cannot sentence substantially
The situation of other early stage bruise.It is every also not into image processing algorithm is systematically reported in loquat OCT image application process
Research is still in the starting stage, and prior art lacks can carry out loquat early stage bruise mirror method for distinguishing.
The content of the invention
Problem present in background technology is directed to, object of the present invention is to provide one kind based on OCT image treatment
Loquat early stage bruise discrimination method, can in automatic identification OCT image loquat bruise defect, and to histiocytic form
Learn parameter and made evaluation, improve detection efficiency, be that loquat on-line checking establishes technology with appearance detecting methods such as synthesized images
Basis.
The technical solution adopted by the present invention is to comprise the following steps：
1) the SD-OCT images with cell details of loquat, the image definition of described SD-OCT images are gathered
Reaching naked eyes can clearly differentiate the cell of loquat epidermis and pulp；
2) bicubic interpolation algorithm is used, down-sampled, downscaled images resolution ratio is carried out to image；
3) to step 2) obtain SD-OCT images carry out Gaussian Blur noise reduction process；
4) line of demarcation of loquat target and background is extracted；
5) peak in line of demarcation and as a reference point is taken, the longitudinal coordinate difference of line of demarcation and reference point is calculated and as position
Each row on line of demarcation in addition to reference point column are carried out upper and lower displacement so that line of demarcation is deformed into along reference point by shifting amount
Straight line；For the pixel for removing image-region, delete, for the new region for moving into image, direct zero padding；
6) 3 × 3 templates are taken, mean filter is carried out to image；
7) threshold value is set, binary conversion treatment is carried out to image, obtain bianry image, the pixel in bianry image is zero pixel
Or non-zero pixels；
8) binary Images Processing is obtained into the corresponding cell compartment of each cell, by being analyzed calculating to cell compartment
Obtain the result that bruise differentiates.
The step 8) it is specially：
8.1) for each pixel of bianry image, the beeline of pixel is calculated：If place pixel is zero pixel, most short
Distance is the distance between place pixel and nearest non-zero pixels；If place pixel is non-zero pixels, beeline is zero；
8.2) watershed algorithm is used, using step 8.1) described in beeline, image is carried out according to cell difference
Segmentation, each cell compartment after being split；
8.3) screened in each cell compartment after singulation, removed the cell compartment of epidermal cell, retained pulp
The cell compartment of cell；Specifically it is expert to be spaced a distance downwards on the basis of reference point and starts to choose remaining image-region
Retained.
8.4) Feret's diameter and equivalent diameter of each cell compartment are calculated, it is straight that reservation Feret's diameter meets Fei Leite
Footpath lower threshold≤R1≤Feret's diameter upper limit threshold, and maximum equivalent diameter is less than the cell compartment of equivalent diameter threshold value；
8.5) by step 8.4) all cell compartments for obtaining calculate summed area table area, average area area, average take
Thunder spy diameter, average equivalent circular diameter and unit area cell number：Summed area table area：It is defined as the area of all cell compartments
Sum；Average area area=total cell region surface product/cell compartment number；Average Feret's diameter=all cell compartments
Feret's diameter sum/cell compartment number；Equivalent diameter sum/the cellular regions of average equivalent circular diameter=all cell compartments
Domain number；The area that unit area cell number=cell compartment number/OCT image occupies；
8.6) the master sample set of normal and bruise loquat is set, the summed area table area of master sample is calculated respectively, is put down
Equal region area, average Feret's diameter, average equivalent circular diameter, unit area cell number threshold value, are judged by cluster analysis
Obtain the result that bruise differentiates.
The step 4) it is specially：
4.1) it is [- 1,1] to set Filtering Template, and first time filtering is carried out to OCT image；
4.2) it is [1, -1] to set Filtering Template, and second filtering is carried out to OCT image；
4.3) filtered image is normalized；
4.4) binaryzation conversion is carried out to image：Thresholding is set up, it is 1, image to set image more than or equal to the pixel of thresholding
It is 0 less than the pixel of thresholding；
4.5) closed operation operation is carried out to image；
4.6) opening operation operation is carried out to image；
4.7) to image after binaryzation in each row pixel, from up to down search for this and list existing first gray value and be
1 pixel is simultaneously recorded as the line of demarcation of target and background.
The step 7) it is specially：Segmentation limit is set, more than or equal to 0 and less than or equal to the pixel of segmentation limit in setting image
It is 1, the pixel that segmentation limit is more than in image is 0.
Image procossing is carried out present invention employs multiple template matches filtering mode, its purpose is exactly from OCT image gray scale
Change in extract loquat maxicell image, and the later stage calculate cell multiple section feature, judge the stasis of blood from characteristic parameter
The presence of wound.Patent before, the main purpose at image early stage is the optical property parameter that local organization is calculated to extract,
And then judging bruise with optical parametric, the technology design of its detection has notable difference compared to existing method herein before.
The invention has the advantages that：
The present invention detects the inside bruise defect of loquat using OCT image, with lossless, quick, inexpensive excellent
Point, substantially increases the efficiency and accuracy of bruise differentiation.
The inventive method employs eucaryotic cell structure parameter as evaluation meanses, to different shape, different size, different thickness
Degree, the place of production, the bruise tissue of growing environment have a universality, and can automatic marking of defects cell position, have compared with other method
There is more preferable positioning precision.
Using cell granulations parameter as evaluation meanses, with reference to the image evened up after conversion, Detection results have the present invention
Certain robustness.
Brief description of the drawings
Fig. 1 is the flow chart of the inventive method.
Fig. 2 is the OCT image of typical loquat sample, wherein (a) is normal zero defect sample, (b) sample pulp organization is deposited
In bruise defect.
Fig. 3 is the original image of embodiment of the present invention image processing procedure.
Fig. 4 is the image that straight line line of demarcation is obtained after the embodiment of the present invention is evened up.
Fig. 5 is the image of all cell compartments after embodiment of the present invention segmentation.
Fig. 6 is the image of reservation cell compartment after embodiment of the present invention screening.
Specific embodiment
Below in conjunction with drawings and Examples, the present invention will be described in further detail.It should be appreciated that described herein
Specific embodiment is only used to explain the present invention, is not intended to limit the present invention.
Embodiments of the invention and its implementation process are as follows：
1) the TELSTO 1300V2 type SD-OCT imagers produced using Thorlabs companies gather the SD- of loquat
40, OCT image sample, wherein 20 contain different degrees of bruise defect, 20 is normal sample；Fig. 2 is wherein 2 allusion quotations
The OCT image of type loquat sample, wherein (a) is normal zero defect sample, there is bruise defect in (b) sample pulp organization.In figure
It can be seen that normal zero defect institutional framework density is higher and compact, and the tissue that there is bruise occurs in that less sparse group of density
Knit.Using only naked eyes, it is impossible to judge its bruise situation.
2) be input into original image as shown in Figure 4, using bicubic interpolation algorithm, image is carried out it is down-sampled, will be original
Image resolution ratio (1625*1024) be contracted to its 1/3.The purpose for reducing sampling is easy for carrying out the quick treatment of image.
3) Gaussian Blur noise reduction process then is carried out to SD-OCT images, eliminates Johnson noise.
4) line of demarcation of loquat target and background is extracted；
4.1) it is [- 1,1] to set template, and first time filtering is carried out to OCT image；
4.2) it is [1, -1] to set template, and second filtering is carried out to OCT image；
Secondary filtering is operated, and is extracted the vertical Mutational part for evening up rear image.
4.3) maximin normalized is carried out to filtered image；
4.4) binaryzation conversion is carried out to image：It is 1.2 to set up thresholding, and it is 1 to set image more than or equal to the pixel of thresholding,
Image is 0 less than the pixel of thresholding；
4.5) 3*3 squares region is taken, closed operation operation is carried out to image；
4.6) 3*3 squares region is taken, opening operation operation is carried out to image.
Make and break computing is carried out for region, background and target has been distinguished.
4.7) to image after binaryzation in each row pixel, from up to down search for this and list existing first gray value and be
1 pixel is simultaneously recorded as the line of demarcation of target and background.
5) peak in line of demarcation is taken, and in this, as reference point；Calculate line of demarcation poor with the longitudinal coordinate of reference point, and
As displacement, upper and lower displacement is carried out to each row on line of demarcation in addition to reference point column so that line of demarcation become through
Cross the straight line of reference point；For the pixel for removing image-region, delete, for the new region for moving into image, direct zero padding；
Even up after converting as shown in Figure 4.
6) 3*3 templates are taken, mean filter is carried out to image, increase the flatness of image.
7) segmentation is set and is limited to 80, carry out binary conversion treatment to image, set in image more than or equal to 0 and less than or equal to point
It is 1 to cut the pixel of limit, and the pixel that segmentation limit is more than in image is 0.
8) for each pixel of bianry image, the beeline of pixel is calculated.For the pixel for being originally 0, it is most short
Distance definition is the distance of 1 pixel closest with it.For example by adjacent zero pixel and nearest non-zero pixels in side it
Between distance be 1, be √ 2 by the distance between zero adjacent pixel of angle and nearest non-zero pixels.For the picture for itself being 1
Element, its beeline is 0.
9) watershed algorithm is used, image is split according to cell difference, each cell compartment after being split,
As shown in Figure 5；
10) screened in each cell compartment after singulation, removed the cell compartment of epidermal cell, retained pulp thin
The cell compartment of born of the same parents；In the present embodiment, on the basis of the straight line line of demarcation where reference point, interception downwards is arrived apart from 0.07mm
Area image in the range of 1mm, the image of reservation is as shown in Figure 6.
11) calculation procedure 10) Feret's diameter and equivalent diameter in each region in the area image, choose Fei Leite
Diameter is in the region of 30 μm to 100 μm of region and maximum equivalent diameter less than 150 μm.
12) by all cell compartments for obtaining calculate summed area table area, average area area, average Feret's diameter,
Average equivalent circular diameter, unit area cell number.
13) the master sample set of normal and bruise loquat is set, the summed area table area, averagely of master sample is calculated respectively
Region area, average Feret's diameter, average equivalent circular diameter, unit area cell number threshold value, are sentenced by cluster analysis
The result of disconnected bruise.Specific implementation is analyzed judgement using KNN clustering methods.
In the present embodiment, each 10 of the two class samples of normal and bruise are taken at random, 20 are counted as master sample, to remaining
Under 20 samples be classified identification, table 1 gives the statistical value of all kinds of parameters, test result indicate that, for 20 samples
Bruise sample and normal sample discrimination in this have reached 100%.
The Weave parameters (95% confidential interval) of the maxicell of table 1
| Parameter | Unit | Normal structure | Bruise tissue |
| Summed area table area | Mm2 | 2.08±1.20 | 1.45±0.07 |
| Average area area | Mm2 | 0.0042±0.0002 | 0.0043±0.0001 |
| Average Feret's diameter | μm | 58.63±1.05 | 59.15±0.85 |
| Average equivalent circular diameter | μm | 40.42±0.73 | 40.62±0.61 |
| Unit area cell number | - | 491.70±25.54 | 340.15±12.34 |
The inventive method is implemented for the full-automatic detection of the early stage bruise of loquat fruit, completes bruise tissue
Subcutaneous cell identify and differentiate, implementation by the bruise tissue to different sources, kind loquat detect obtain it is stronger
Detection reliability, improves detection efficiency.
In embodiments of the present invention, during those of ordinary skill in the art are further appreciated that and realize above-described embodiment method
All or part of step can be by program to instruct the hardware of correlation to complete, and described program can be stored in a meter
In calculation machine read/write memory medium, described storage medium, including ROM/RAM, disk, CD etc..
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, it is all in essence of the invention
Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.
Claims (5)
1. it is a kind of based on OCT image treatment loquat early stage bruise discrimination method, it is characterised in that：Comprise the following steps：
1) the SD-OCT images with cell image details of loquat are gathered；
2) bicubic interpolation algorithm is used, down-sampled, downscaled images resolution ratio is carried out to image；
3) to step 2) obtain SD-OCT images carry out Gaussian Blur noise reduction process；
4) line of demarcation of loquat target and background is extracted；
5) peak in line of demarcation and as a reference point is taken, the longitudinal coordinate difference of line of demarcation and reference point is calculated and as displacement
Each row on line of demarcation in addition to reference point column are carried out upper and lower displacement so that line of demarcation is deformed into along reference point by amount
Straight line；
6) 3 × 3 templates are taken, mean filter is carried out to image；
7) threshold value is set, binary conversion treatment is carried out to image, obtain bianry image；
8) binary Images Processing is obtained into the corresponding cell compartment of each cell, is obtained by being analyzed calculating to cell compartment
The result that bruise differentiates.
2. a kind of loquat early stage bruise discrimination method based on OCT image treatment according to claim 1, its feature exists
In：The image definition of described SD-OCT images reaches naked eyes can clearly differentiate the cell of loquat epidermis and pulp.
3. a kind of loquat early stage bruise discrimination method based on OCT image treatment according to claim 1, its feature exists
In：The step 8) it is specially：
8.1) for each pixel of bianry image, the beeline of pixel is calculated：If place pixel is zero pixel, beeline
It is the distance between place pixel and nearest non-zero pixels；If place pixel is non-zero pixels, beeline is zero；
8.2) watershed algorithm is used, using step 8.1) described in beeline, image is split according to cell difference,
Each cell compartment after being split；
8.3) screened in each cell compartment after singulation, removed the cell compartment of epidermal cell, retained flesh cell
Cell compartment；
8.4) Feret's diameter and equivalent diameter of each cell compartment are calculated, is retained Feret's diameter and is met under Feret's diameter
Limit threshold value≤R1≤Feret's diameter upper limit threshold, and maximum equivalent diameter is less than the cell compartment of equivalent diameter threshold value；
8.5) by step 8.4) all cell compartments for obtaining calculate summed area table area, average area area, average Fei Leite
Diameter, average equivalent circular diameter and unit area cell number：
Summed area table area：It is defined as the area sum of all cell compartments；
Average area area=total cell region surface product/cell compartment number；
Feret's diameter sum/cell compartment the number of average Feret's diameter=all cell compartments；
Equivalent diameter sum/cell compartment the number of average equivalent circular diameter=all cell compartments；
The area that unit area cell number=cell compartment number/OCT image occupies；
8.6) the master sample set of normal and bruise loquat is set, summed area table area, the average area of master sample is calculated respectively
Domain area, average Feret's diameter, average equivalent circular diameter, unit area cell number threshold value, judge to obtain by cluster analysis
The result that bruise differentiates.
4. a kind of loquat early stage bruise discrimination method based on OCT image treatment according to claim 1, its feature exists
In：The step 4) it is specially：
4.1) it is [- 1,1] to set Filtering Template, and first time filtering is carried out to OCT image；
4.2) it is [1, -1] to set Filtering Template, and second filtering is carried out to OCT image；
4.3) filtered image is normalized；
4.4) binaryzation conversion is carried out to image：Thresholding is set up, the pixel for setting image more than or equal to thresholding is 1, and image is less than
The pixel of thresholding is 0；
4.5) closed operation operation is carried out to image；
4.6) opening operation operation is carried out to image；
4.7) to image after binaryzation in each row pixel, it is 1 from up to down to search for this and list existing first gray value
Pixel is simultaneously recorded as the line of demarcation of target and background.
5. a kind of loquat early stage bruise discrimination method based on OCT image treatment according to claim 1, its feature exists
In：The step 7) it is specially：Set and split limit, it is 1 to set the pixel limited more than or equal to 0 and less than or equal to segmentation in image,
The pixel for being more than segmentation limit in image is 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710071158.1A CN106780347B (en) | 2017-02-09 | 2017-02-09 | Early loquat bruise identification method based on OCT image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710071158.1A CN106780347B (en) | 2017-02-09 | 2017-02-09 | Early loquat bruise identification method based on OCT image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106780347A true CN106780347A (en) | 2017-05-31 |
| CN106780347B CN106780347B (en) | 2020-03-03 |
Family
ID=58955646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710071158.1A Active CN106780347B (en) | 2017-02-09 | 2017-02-09 | Early loquat bruise identification method based on OCT image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106780347B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527365A (en) * | 2017-08-18 | 2017-12-29 | 郑州云海信息技术有限公司 | A kind of method and device of dynamic calculation class circle object morphology diameter |
| CN108776967A (en) * | 2018-06-12 | 2018-11-09 | 塔里木大学 | A kind of bergamot pear bruise discrimination method |
| CN110264472A (en) * | 2019-05-29 | 2019-09-20 | 浙江科技学院 | A kind of nearly subcutaneous cell noninvasive imaging method of fruit based on SD-OCT |
| CN111624659A (en) * | 2020-06-05 | 2020-09-04 | 中油奥博(成都)科技有限公司 | Time-varying band-pass filtering method and device for seismic data |
| CN111932499A (en) * | 2020-07-10 | 2020-11-13 | 深圳市瑞沃德生命科技有限公司 | Method, device and system for calculating cell diameter |
| CN113409302A (en) * | 2021-07-13 | 2021-09-17 | 浙江科技学院 | Corn kernel early mildew identification method based on OCT image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059452A (en) * | 2007-05-29 | 2007-10-24 | 浙江大学 | Fruit quality damage-free detection method and system based on multiple spectral imaging technique |
| US20160174830A1 (en) * | 2013-07-31 | 2016-06-23 | The Board Of Trustees Of The Leland Stanford Junior University | Method and System for Evaluating Progression of Age-Related Macular Degeneration |
| CN105787924A (en) * | 2016-02-01 | 2016-07-20 | 首都医科大学 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
| CN105891229A (en) * | 2014-09-05 | 2016-08-24 | 熊菊莲 | Method for determining characteristic wavelength for spectral image analysis and detection of surfaces of fruits |
| CN106023158A (en) * | 2016-05-10 | 2016-10-12 | 浙江科技学院 | SD-OCT-image-based nacre layer defect identification method for fresh water non-nucleated pearl |
| CN106332713A (en) * | 2016-08-16 | 2017-01-18 | 浙江科技学院 | Method for identifying early-phase bruise of loquat through SD-OCT image |
-
2017
- 2017-02-09 CN CN201710071158.1A patent/CN106780347B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059452A (en) * | 2007-05-29 | 2007-10-24 | 浙江大学 | Fruit quality damage-free detection method and system based on multiple spectral imaging technique |
| US20160174830A1 (en) * | 2013-07-31 | 2016-06-23 | The Board Of Trustees Of The Leland Stanford Junior University | Method and System for Evaluating Progression of Age-Related Macular Degeneration |
| CN105891229A (en) * | 2014-09-05 | 2016-08-24 | 熊菊莲 | Method for determining characteristic wavelength for spectral image analysis and detection of surfaces of fruits |
| CN105787924A (en) * | 2016-02-01 | 2016-07-20 | 首都医科大学 | Method for measuring diameter of maximum choroid blood vessel based on image segmentation |
| CN106023158A (en) * | 2016-05-10 | 2016-10-12 | 浙江科技学院 | SD-OCT-image-based nacre layer defect identification method for fresh water non-nucleated pearl |
| CN106332713A (en) * | 2016-08-16 | 2017-01-18 | 浙江科技学院 | Method for identifying early-phase bruise of loquat through SD-OCT image |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527365A (en) * | 2017-08-18 | 2017-12-29 | 郑州云海信息技术有限公司 | A kind of method and device of dynamic calculation class circle object morphology diameter |
| CN108776967A (en) * | 2018-06-12 | 2018-11-09 | 塔里木大学 | A kind of bergamot pear bruise discrimination method |
| CN110264472A (en) * | 2019-05-29 | 2019-09-20 | 浙江科技学院 | A kind of nearly subcutaneous cell noninvasive imaging method of fruit based on SD-OCT |
| CN110264472B (en) * | 2019-05-29 | 2021-05-04 | 浙江科技学院 | SD-OCT-based fruit hypodermal cell nondestructive imaging method |
| CN111624659A (en) * | 2020-06-05 | 2020-09-04 | 中油奥博(成都)科技有限公司 | Time-varying band-pass filtering method and device for seismic data |
| CN111932499A (en) * | 2020-07-10 | 2020-11-13 | 深圳市瑞沃德生命科技有限公司 | Method, device and system for calculating cell diameter |
| CN111932499B (en) * | 2020-07-10 | 2023-12-22 | 深圳市瑞沃德生命科技有限公司 | Cell diameter calculation method, device and system |
| CN113409302A (en) * | 2021-07-13 | 2021-09-17 | 浙江科技学院 | Corn kernel early mildew identification method based on OCT image |
| CN113409302B (en) * | 2021-07-13 | 2023-07-07 | 浙江科技学院 | OCT image-based corn kernel early mildew identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106780347B (en) | 2020-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106780347A (en) | A kind of loquat early stage bruise discrimination method based on OCT image treatment | |
| Li et al. | Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method | |
| CN106023158B (en) | The fresh water pipless pearl pearly layer defect identification method of SD-OCT images | |
| Pujari et al. | Grading and classification of anthracnose fungal disease of fruits based on statistical texture features | |
| Xiao-bo et al. | In-line detection of apple defects using three color cameras system | |
| Li et al. | Detection of early decayed oranges based on multispectral principal component image combining both bi-dimensional empirical mode decomposition and watershed segmentation method | |
| Zapotoczny et al. | Application of image analysis for the varietal classification of barley:: Morphological features | |
| Lu et al. | Detection of surface and subsurface defects of apples using structured-illumination reflectance imaging with machine learning algorithms | |
| NL2024774B1 (en) | Blood leukocyte segmentation method based on adaptive histogram thresholding and contour detection | |
| CN106332713B (en) | A kind of loquat early stage bruise discrimination method of SD-OCT image | |
| CN110082298B (en) | Hyperspectral image-based wheat variety gibberellic disease comprehensive resistance identification method | |
| CN104990892B (en) | The spectrum picture Undamaged determination method for establishing model and seeds idenmtification method of seed | |
| CN106815819B (en) | More strategy grain worm visible detection methods | |
| CN110596117A (en) | Hyperspectral imaging-based rapid nondestructive detection method for apple surface damage | |
| CN103394472A (en) | Method for detecting and grading greening potatoes based on machine vision | |
| CN108388853B (en) | Stepwise reconstruction and counting method for leucocyte and platelet coexistence hologram | |
| CN106780427B (en) | A kind of bergamot pear bruise discrimination method based on OCT image | |
| CN110622651A (en) | Method for detecting quality of sweet corn | |
| Zuñiga et al. | Grape maturity estimation based on seed images and neural networks | |
| CN110779875A (en) | Method for detecting moisture content of winter wheat ear based on hyperspectral technology | |
| Guo et al. | Hyperspectral image analysis for the evaluation of chilling injury in avocado fruit during cold storage | |
| Moncayo et al. | A grading strategy for nuclear pleomorphism in histopathological breast cancer images using a bag of features (bof) | |
| CN111562273A (en) | Hyperspectrum-based fish water jet descaling slight damage visualization method | |
| Nie et al. | Machine vision-based apple external quality grading | |
| Liu et al. | Application of an improved watershed algorithm based on distance map reconstruction in bean image segmentation |
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 |